research
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external primary sources (documentation, APIs, source code) and processes it to generate Markdown files.
- Ingestion points: External URLs and source code files within the repository (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or warnings for the agent to ignore instructions embedded within the research material.
- Capability inventory: The agent possesses file-writing capabilities to record findings (SKILL.md).
- Sanitization: There are no explicit instructions to validate or sanitize the gathered information before committing it to the repository.
Audit Metadata