ChatGPT Plugin

Pi Security

Investigate security findings

Brand: Pi Security

Category: Security
Primary Subcategory: Application Security & Vulnerability Management

Integration details

Description

Pi Security helps users investigate security findings, review threat-model, Code Gatekeeper, and software-dependency posture, retrieve remediation and secure-development guidance, and take confirmed actions such as starting reviews, importing reports, updating issue state, and creating remediation pull requests.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Security
Primary Subcategory: Application Security & Vulnerability Management
Secondary Subcategories: None listed
Brand: Pi Security
Access: Account required
First tracked: 2026-10-09
Tool count: 42
Geography: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competing in ChatGPT Application Security & Vulnerability Management

View Category

Listed in alphabetical order

Primary Subcategory

Codex Security AccessComing soonGet notified

Codex Security CloudComing soonGet notified

FingerprintComing soonGet notified

FlawPilotComing soonGet notified

NPMScanComing soonGet notified

Pi SecurityComing soonGet notified

Tools

42 tools agents can invoke

Replies to an existing Code Gatekeeper issue thread in the connected source control provider.
pi_gatekeeper_issue_comment
Starts a design review from inline Markdown design-document content.
pi_design_review_markdown_create
Starts a design review for a supported Confluence or Notion design document URL.
pi_design_review_url_create
Creates remediation pull requests for all current repositories or an explicit repository subset for a finding by FND-XXX display ID, UUID, or Pi finding URL. Set exactly one of allRepositories: true or repositories. Publication resolves current targets independently of discovery. If a result is replacement_confirmation_required, ask the user to confirm replacement for the named repository and call again with that repositories array and confirmReplacement: true.
pi_finding_remediation_pr_create
Records feedback when playbook guidance is wrong, stale, incomplete, or missing context.
pi_playbook_comment_create
Enriches one organizational memory from bounded feedback and returns its normalized post-mutation state.
pi_memory_enrich
Fetches sanitized plan-only SBOM package remediation content for an existing package remediation plan. Requires codebase to identify the repository slug or ID.
pi_package_remediation_plan_fetch
Fetches sanitized remediation plan-only content for a finding by FND-XXX display ID, UUID, or Pi finding URL.
pi_remediation_plan_fetch
Reversibly suppresses one organizational memory and returns its normalized post-mutation state.
pi_memory_forget
Gets rich Code Gatekeeper detail for a single PR security review.
pi_gatekeeper_pr_get
Gets rich Code Gatekeeper detail for a single PR issue.
pi_gatekeeper_issue_get
Gets one normalized dependency summary by its exact purlSlug.
pi_sbom_dependency_get
Gets a design review by its full UUID, with lifecycle state and completed review results when available.
pi_design_review_get
Gets a finding by FND-XXX display ID, UUID, or Pi finding URL.
pi_finding_get
Gets the activity timeline for a finding by FND-XXX display ID, UUID, or Pi finding URL.
pi_finding_activity_get
Gets normalized variant detail by its canonical FND-XXX-V-YYY reference.
pi_finding_variant_get
Gets one normalized organizational memory in any lifecycle state by its exact MEM-<n> reference.
pi_memory_get
Gets threat-model application metadata and ordered section slugs/titles without section content. Call pi_threat_model_app_section_get with the returned app ID and a returned section slug to retrieve one section.
pi_threat_model_app_get
Gets one complete threat-model application section, including Markdown content, by the app ID and a section slug returned by pi_threat_model_app_get.
pi_threat_model_app_section_get
Lists Code Gatekeeper PR security reviews visible to the authenticated tenant user.
pi_gatekeeper_prs_list
Lists Code Gatekeeper PR issues visible to the authenticated tenant user.
pi_gatekeeper_issues_list
Lists normalized dependencies visible to the authenticated tenant user using repository, vulnerability, upgrade, and reachability filters with cursor pagination.
pi_sbom_dependencies_list
Lists normalized repository and manifest usage for an exact dependency purlSlug with cursor pagination.
pi_sbom_dependency_repositories_list
Lists normalized vulnerabilities for an exact dependency purlSlug with cursor pagination.
pi_sbom_dependency_vulnerabilities_list
Lists design reviews visible to the authenticated tenant user using canonical filters and cursor pagination.
pi_design_reviews_list
Lists the current accessible remediation pull request repositories for a finding using bounded cursor pagination.
pi_finding_remediation_pr_targets_list
Lists normalized variants for a finding by its FND-XXX reference using bounded opaque-cursor pagination.
pi_finding_variants_list
Lists findings visible to the authenticated tenant user using the provided filters.
pi_findings_list
Lists normalized active organizational memories visible to the authenticated tenant user using scope and memory-type filters with bounded cursor pagination.
pi_memories_list
Lists threat-model applications visible to the authenticated tenant user.
pi_threat_model_apps_list
Starts or reuses SBOM package remediation plan generation and returns the current plan state. Requires codebase to identify the repository slug or ID.
pi_package_remediation_plan_prepare
Searches tenant knowledge for repo, architecture, and security context visible to the authenticated user.
pi_knowledgebase_query
Retrieves repo-local secure implementation guidance for a natural-language task.
pi_playbook_task_query
Reinforces one organizational memory and returns its normalized post-mutation state.
pi_memory_reinforce
Reopens a resolved finding by FND-XXX display ID, UUID, or Pi finding URL.
pi_finding_reopen
Resolves a finding by FND-XXX display ID, UUID, or Pi finding URL using an existing human resolution reason.
pi_finding_resolve
Restores one suppressed or superseded organizational memory and returns its normalized post-mutation state.
pi_memory_restore
Semantically searches active organizational memories visible to the authenticated tenant user and returns up to 10 normalized matches.
pi_memories_search
Returns the current Pi tenant and access context for connection verification.
whoami
Removes the caller's reinforcement from one organizational memory and returns its normalized post-mutation state.
pi_memory_unreinforce
Reopens one Code Gatekeeper issue or marks it false positive or accepted risk, with an optional reason.
pi_gatekeeper_issue_update_status
Uploads Markdown report content and starts the tenant report-ingestion workflow.
pi_report_markdown_upload

FAQs

Pi Security ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Pi Security's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are Pi Security alternatives on ChatGPT?

As of 2026-10-09, Pi Security competes with Codex Security Access, Codex Security Cloud, Fingerprint, FlawPilot, NPMScan, Orca Security, Safeguard, Strix and 1 more in ChatGPT Application Security & Vulnerability Management, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.