hiring-strategy

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious behaviors detected in the skill instructions or reference files.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill is designed to ingest and analyze untrusted user-provided data (source code and startup plans) but lacks the high-risk capabilities necessary for exploitation.
  • Ingestion points: Processes user-provided software code and hiring queries.
  • Boundary markers: Absent; the skill relies on internal model logic to distinguish between instructions and data.
  • Capability inventory: Limited to generating natural language advice and code reviews; no subprocess execution, network operations, or file-write capabilities were found.
  • Sanitization: None detected for user-provided data.
  • [PROMPT_INJECTION] (SAFE): The instruction to 'ignore generic approaches' is a standard domain-grounding technique and does not attempt to bypass core AI safety filters or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM