procedural-skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user intent, procedures, and examples to generate executable instructions, creating a surface where malicious input could influence subsequent agent behavior.
- Ingestion points: User-provided intent and supplied procedures (found in SKILL.md, Step 1).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the source material are defined.
- Capability inventory: The skill is capable of saving generated skills and resources to the file system (found in SKILL.md, Step 3).
- Sanitization: No explicit validation of user-provided content or sanitization of target file paths is defined beyond qualitative checks.
- [DYNAMIC_EXECUTION]: The verification process instructs the agent to 'exercise helpers' and 'run a representative task' using the newly created skill code (found in SKILL.md, Step 5).
Audit Metadata