release-highlights
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data that could contain malicious instructions.
- Ingestion points: The skill ingests release versions, tags, changelog ranges, and PR sets directly from the user's environment or external repositories (SKILL.md).
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the changelog or PR data.
- Capability inventory: No dangerous capabilities (subprocess execution, network operations, or file system writes) were detected in the skill instructions.
- Sanitization: No sanitization, escaping, or filtering of the ingested content is described in the workflow.
Audit Metadata