intercom-ci-integration

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh command-line tool to manage GitHub Actions secrets (gh secret set, gh secret list) and uses curl within a GitHub Actions workflow to verify connectivity to the Intercom API.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to configure workflows that interact with Intercom's official API (https://api.intercom.io/me) and utilizes official GitHub Actions maintained by the GitHub organization (actions/checkout, actions/setup-node, actions/upload-artifact).
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it ingests untrusted data from the local project environment to determine its actions.
  • Ingestion points: The skill reads the content of package.json to identify existing test and build scripts (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content within the ingested files were identified.
  • Capability inventory: The skill has the capability to write and edit files (Write, Edit) and execute specific shell commands via Bash(gh:*) (SKILL.md).
  • Sanitization: No sanitization or validation of the content read from package.json was identified before its use in generating workflow files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:49 AM
Security Audit — agent-trust-hub — intercom-ci-integration