human-english
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate utility for improving text clarity and removing AI-writing tells. All referenced files and logic are instructional in nature and align with its stated purpose.\n- [PROMPT_INJECTION]: The skill processes untrusted user-provided text, which represents an indirect prompt injection surface. This is a characteristic of text-processing skills and is mitigated by the skill's explicit rules forbidding modifications to code, identifiers, and configuration.\n
- Ingestion points: User-provided text and files processed via 'Read' and 'Grep' tools as defined in SKILL.md.\n
- Boundary markers: Absent; the skill does not define specific delimiters for isolating input text from instructions.\n
- Capability inventory: File system modification access (Write, Edit) and user interaction (AskUserQuestion) as listed in the allowed-tools of SKILL.md.\n
- Sanitization: No structural sanitization is specified; however, the 'Untouchables' and 'Self-check' sections in SKILL.md provide strong behavioral constraints that discourage the modification of code and critical system files.
Audit Metadata