checking-deploy-timing

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including GitHub pull request metadata and internal PostHog deployment annotations which could potentially contain attacker-controlled text.\n
  • Ingestion points: Data enters the agent context via the output of posthog:annotations-list and GitHub CLI commands such as gh search prs and gh pr view.\n
  • Boundary markers: The skill does not provide specific instructions to use delimiters or ignore instructions that might be embedded in commit messages or PR titles.\n
  • Capability inventory: The skill is capable of executing shell commands through the gh CLI and querying project metadata.\n
  • Sanitization: No sanitization logic is specified for the data retrieved from external API responses before it is used to determine deployment timing.\n- [COMMAND_EXECUTION]: The skill leverages the GitHub CLI to interact with the version control history.\n
  • Patterns detected: The instructions guide the agent to use gh search prs, gh pr view, and gh api to search for and verify merge commits and their ancestry.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:58 AM
Security Audit — agent-trust-hub — checking-deploy-timing