agent-compliance-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directly interpolates external task arguments into the prompt without using boundary markers, sanitization, or instructions to ignore potential commands embedded in data.
- Ingestion points: SKILL.md via the $ARGUMENTS variable.
- Boundary markers: Absent; the user-provided task input is appended directly to the end of the markdown file.
- Capability inventory: The skill uses the 'general-purpose' agent configuration, which typically includes file system access and terminal execution capabilities.
- Sanitization: No sanitization, escaping, or filtering of the $ARGUMENTS content is performed before processing.
Audit Metadata