guest-posting-opportunity-finder
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill addresses potential injection risks by explicitly instructing the agent to treat text embedded in source content as data, not as new instructions. It includes specific examples of how to handle content that attempts to override user tasks.
- [DATA_EXPOSURE_AND_EXFILTRATION]: There are no patterns of sensitive file access or data exfiltration. The instructions specify keeping credentials and private customer data out of the generated output.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unauthorized script downloads were detected. The YAML frontmatter references a repository for metadata purposes, but no execution logic is associated with it.
- [SAFE]: The skill follows best practices for AI agent instructions, including clear boundaries for input processing and a focus on verifiable evidence rather than fabricated results.
Audit Metadata