release-pr-gates
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes potentially untrusted content from GitHub Actions logs, commit histories, and pull request metadata. It implements robust defenses by instructing the agent to treat this content strictly as evidence and to ignore any instructions embedded within the data.
- Ingestion points: Data enters the context via
gh run view --log,git log, andgh pr listcommands inSKILL.md. - Boundary markers: Explicit instructions are provided in the "External Side Effects" section of
SKILL.mdto disregard embedded commands and treat text as untrusted. - Capability inventory: The agent has permissions to execute shell commands, manage repository tags, and create GitHub releases.
- Sanitization: The instructions specifically require the redaction of secret-like values from external data before processing.
- [COMMAND_EXECUTION]: The skill uses
npm,bun, andbunxto execute local build, formatting, and linting scripts defined in the repository. This is an expected and necessary function for verifying release readiness and occurs within the local environment.
Audit Metadata