cc-pseudocode-programming
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied routine requirements and logic to generate pseudocode and final implementation code. This creates a standard surface where malicious instructions could be embedded in the design data.
- Ingestion points: User-provided routine names, purposes, inputs, outputs, and logic descriptions in the SKILL.md interaction loop.
- Boundary markers: Absent. There are no specific delimiters or instructions for the agent to treat user-provided logic strictly as data or to ignore embedded directives.
- Capability inventory: The agent is instructed to generate source code and header comments based on the user's intent.
- Sanitization: No sanitization or validation logic is defined for the input routine descriptions.
Audit Metadata