hiring
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes potentially untrusted data from external sources and user inputs to generate hiring documentation.\n
- Ingestion points: Content is read from
BUSINESS_CONTEXT.mdand user-provided candidate background summaries.\n - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to distinguish between trusted instructions and potentially malicious commands embedded in the ingested data.\n
- Capability inventory: The skill allows writing to the local file system, including creating or updating
BUSINESS_CONTEXT.mdand files within thehiring/directory.\n - Sanitization: No evidence of validation, escaping, or filtering of the ingested data is present before it is used in prompt interpolation.
Audit Metadata