improve-agent-readiness
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes an external "agent readiness report" to identify missing features and propose repository improvements. This creates a surface for indirect prompt injection if the report contains instructions designed to manipulate the agent's code generation.
- Ingestion points: SKILL.md (Step 1: Read the report)
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: File writing and Git commits (SKILL.md, Step 3: Implement on request).
- Sanitization: None detected; however, the skill requires user approval before implementation, which serves as a significant mitigation.
Audit Metadata