hold-person
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a procedure for processing user-provided targets (accounts, processes, or workflows).
- Ingestion points: Target descriptions provided via the example invocation in
SKILL.md. - Boundary markers: Step 1 in the Procedure requires restating the target and no-touch boundaries.
- Capability inventory: No subprocess calls, network operations, or file-writing tools are included in the skill.
- Sanitization: No explicit sanitization or filtering of input data is mentioned.
- [NO_CODE]: The skill consists entirely of documentation and instructions in markdown format with YAML metadata. It does not include or reference any scripts, executables, or code-based configurations.
Audit Metadata