content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external research and user-provided writing samples. \n
- Ingestion points: SKILL.md (Instructions 3: 'Conduct Research' and Instruction 5: 'Provide Section-by-Section Feedback'). \n
- Boundary markers: The instructions do not define clear delimiters or 'ignore' warnings for content extracted during the research phase. \n
- Capability inventory: The skill enables the agent to write files (Instruction 1, 'How to Use' setup commands) and perform web searches for research. \n
- Sanitization: No sanitization or validation of external content is specified. \n- [COMMAND_EXECUTION]: The skill documentation includes standard shell commands for setting up a local writing environment. \n
- Evidence:
mkdir ~/writing/my-article-title,cd ~/writing/my-article-title,touch article-draft.md. \n - Context: These are benign commands used for directory and file creation within the user's home directory.
Audit Metadata