brief-recruitment-profile
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface. The skill ingests untrusted data from multiple external web sources (careers pages, LinkedIn, Glassdoor) which is then used to generate research briefs.\n
- Ingestion points: WebFetch and WebSearch tool calls in SKILL.md.\n
- Boundary markers: Absent; no specific instructions to the agent to disregard instructions found within the fetched content.\n
- Capability inventory: Write access to the file system and limited Bash utility access (mkdir, test).\n
- Sanitization: No sanitization of the fetched data is performed before processing.\n- [COMMAND_EXECUTION]: Potential for path manipulation. The skill uses the user-supplied --slug argument to construct file system paths for mkdir and Write operations without explicit validation, which could be used for path traversal to write files outside the intended directory structure.\n- [EXTERNAL_DOWNLOADS]: Fetches data from external platforms including LinkedIn and Glassdoor. These are well-known services used for the skill's primary research purpose.
Audit Metadata