writing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, hardcoded credentials, or dangerous commands were detected. The instructions focus on documentation best practices and specify that code behavior must not change when editing comments.
- [NO_CODE]: The skill consists entirely of markdown files and does not include any executable scripts, binary files, or external software dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it processes and revises external text data.
- Ingestion points: Technical documentation, READMEs, and code comments.
- Boundary markers: Absent; no specific delimiters are defined for user-provided text.
- Capability inventory: Documentation drafting and comment rewriting; no system-level commands or network operations are involved.
- Sanitization: No explicit sanitization or filtering of input text is performed.
- Note: The risk is considered safe because the skill's instructions specifically forbid changes to executable code and require validation that project tests continue to pass.
Audit Metadata