research-lib
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external sources to generate documentation.
- Ingestion points: Research results from the Gemini CLI and manual web search results as defined in SKILL.md.
- Boundary markers: Absent. The skill does not use delimiters or instructions to ignore embedded commands within the research data.
- Capability inventory: The skill writes documentation files to the .claude/docs/libraries/ directory, which the agent may read later.
- Sanitization: Absent. The skill does not validate or sanitize content fetched from external sources before saving it locally.
- [COMMAND_EXECUTION]: The skill executes external shell commands as part of its core functionality.
- Evidence: Shell execution of the gemini CLI tool with parameters derived from skill arguments in SKILL.md.
Audit Metadata