pr-landing-discipline
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell scripts to interact with the GitHub CLI (gh) and git for tasks such as fetching PR metadata, analyzing diffs, and performing merges or pushes.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from PR titles, bodies, and comments to automate triage and PII checks.
- Ingestion points: Content is fetched using
gh pr viewandgh apicalls inSKILL.md. - Boundary markers: The instructions do not define explicit delimiters to isolate untrusted PR content from the agent's core instructions.
- Capability inventory: The skill can execute subprocesses (gh, git, grep, sed), write to temporary files (mktemp), and perform repository operations via the GitHub API (merge, push, label management).
- Sanitization: No explicit validation or filtering is applied to the content of PR comments before they are interpreted by the agent's triaging logic.
- [DATA_EXPOSURE]: The skill's redaction logic reads extensive PR metadata, commit history, and discussion content into the agent's context to check for PII leakage. While intended for security, this grants the agent broad access to repository content.
Audit Metadata