release-readiness-auditor
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text and markdown templates for software release auditing. It does not contain any scripts, executable code, external downloads, or requests for high-privilege tools.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing external project data, which introduces an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read project-level instructions, architecture, and requirements from the project being audited (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded within the project documentation it reads.
- Capability inventory: No specific tools (such as shell access or network tools) are requested in the skill's YAML frontmatter.
- Sanitization: No input sanitization or validation steps are prescribed for the external data being processed.
- Note: While the ingestion of untrusted data is a theoretical risk, the lack of dangerous capabilities within the skill and the inclusion of explicit safety instructions in the quality standard (references/quality-standard.md) effectively mitigate this concern.
Audit Metadata