capgo-release-workflows
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and metadata. It does not include any scripts, binary executables, or shell command injections.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather requirements from the user (Step 1: Identify Release Requirements). While this is an ingestion point for untrusted data, the skill has no capabilities (subprocess calls, file writes, or network operations) that could be exploited by an injection attack.
- Ingestion points: Step 1 in
SKILL.mdprocesses user requirements. - Boundary markers: Not present.
- Capability inventory: None (no code or tools defined in this skill).
- Sanitization: Not applicable as there is no execution logic.
- [SAFE]: External references in
metadata.jsonpoint to official documentation and the vendor's primary website. No suspicious or obfuscated network patterns were detected.
Audit Metadata