sourcing-outreach
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: An indirect prompt injection surface exists because the skill processes untrusted data from candidate research.\n
- Ingestion points: Candidate background details, including LinkedIn profiles, blog posts, and open-source contributions mentioned in the 'Context Required' and 'Workflow' sections of SKILL.md.\n
- Boundary markers: None; the skill does not use delimiters or provide instructions to the agent to ignore potential commands embedded within candidate data.\n
- Capability inventory: The skill is limited to generating text for outreach and follow-up sequences; no subprocess calls, network requests, or file-writing operations were identified.\n
- Sanitization: None; the instructions do not include any steps to validate or escape the external content before it is processed by the agent.\n- [NO_CODE]: This skill consists solely of markdown instructions and templates; it contains no executable scripts or binary files.
Audit Metadata