complexitysmash
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided codebase content, which represents a potential surface for indirect prompt injection where malicious instructions could be embedded in the code being audited.\n
- Ingestion points: The agent is instructed to map the shape of the system and identify complexity hotspots by reading project files as specified in
SKILL.md.\n - Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions within the files it analyzes.\n
- Capability inventory: The skill requires the agent to read and evaluate repository-wide files to produce architectural findings.\n
- Sanitization: There are no explicit instructions to sanitize or validate the content of the external code files being processed.
Audit Metadata