byted-recruitment-general
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes candidate profile data from untrusted external websites.
- Ingestion points: Candidate profiles scraped from LinkedIn, Liepin, and Maimai as defined in SKILL.md.
- Boundary markers: No explicit markers are present to separate untrusted profile data from agent instructions.
- Capability inventory: The skill uses browser automation and file system write access in the workspace directory.
- Sanitization: No sanitization or validation logic is described for the data extracted from candidate profiles.
Audit Metadata