wrap
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data via the $ARGUMENTS placeholder across multiple files including SKILL.md and all files in the commands directory.
- Ingestion points: Untrusted data enters the agent context via the $ARGUMENTS variable at the end of each template.
- Boundary markers: The skill lacks explicit delimiters or instructions (e.g., ignore embedded directives) to prevent the agent from following instructions hidden within the user-provided arguments.
- Capability inventory: A review of all files (SKILL.md, attain-distance.md, prepare.md, reality-test.md, widen.md, wrap.md) confirms the skill has no high-privilege capabilities such as file writing, network access, or subprocess execution.
- Sanitization: No evidence of input validation, filtering, or escaping was found in the skill templates.
Audit Metadata