candango-discover

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is documentation-centric, providing templates and instructional guidelines for project planning. It does not contain executable code, shell scripts, or external network requests.\n- [PROMPT_INJECTION]: The skill ingests user-provided feature requirements and plans to generate documentation. While it acts as a data processing surface, the risk is negligible as it only outputs text-based markdown files to the local documentation directory.\n
  • Ingestion points: User-provided feature plans and requirements as specified in SKILL.md.\n
  • Boundary markers: No explicit markers or instructions to ignore embedded instructions are present.\n
  • Capability inventory: The skill defines write operations for documentation files in docs/features/ and docs/adr/.\n
  • Sanitization: No input sanitization is performed, but the output is restricted to documentation content without execution capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 03:31 PM
Security Audit — agent-trust-hub — candango-discover