sales-career

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data, such as interview answers and resume bullets, to generate career roadmaps and artifacts. This creates a surface for indirect prompt injection where a user could attempt to influence agent behavior via embedded instructions. 1. Ingestion points: User data enters the context via the 'Interview' section and the 'Track record' evidence bank in SKILL.md. 2. Boundary markers: The instructions do not define explicit delimiters (like XML tags) or 'ignore embedded instructions' warnings for user-provided strings. 3. Capability inventory: The skill uses web search to update benchmarks and file system operations to generate roadmap documents. 4. Sanitization: The skill incorporates an 'Evidence audit' and a 'Quality gate' in SKILL.md that require the agent to verify arithmetic and provenance of claims, providing a logical filter against malicious or deceptive inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:18 PM
Security Audit — agent-trust-hub — sales-career