release-notes
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from potentially untrusted sources, such as existing repository release notes and CHANGELOG files.
- Ingestion points: Uses
gh release viewto read existing release bodies and reads the project's localCHANGELOGfile (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or "ignore instructions" prompts when processing these files.
- Capability inventory: The skill has the capability to write to the repository using
gh release editand suggests executing code samples against published artifacts to verify release claims. - Sanitization: No specific escaping or validation logic is defined for the content extracted from the changelogs or previous releases.
- Note: This represents a standard functional surface for a release automation tool and does not indicate malicious intent.
Audit Metadata