ambassador-finder
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of instructional Markdown files. There are no executable scripts, binaries, or configuration files that trigger code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external data from websites, articles, and social media profiles. This introduces a surface where malicious instructions could be embedded in the data being processed. However, since the skill has no access to sensitive tools or file systems, the risk remains low.
- Ingestion points: Social media activity, industry articles, and candidate profiles (SKILL.md, Step 2; screening-rubric.md, Step 3b).
- Boundary markers: None provided.
- Capability inventory: Information extraction and table generation.
- Sanitization: None.
Audit Metadata