git-release
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: Vulnerability to indirect prompt injection surface in SKILL.md. 1. Ingestion points: commit history and pull request titles are ingested to generate release notes. 2. Boundary markers: absent, as there are no delimiters or instructions to ignore embedded commands within the ingested text. 3. Capability inventory: none, the skill does not include any scripts or automated execution logic. 4. Sanitization: absent, with no validation or filtering of the source git metadata.
- [NO_CODE]: This skill consists entirely of natural language instructions and metadata with no accompanying executable code or scripts.
Audit Metadata