win-loss-analysis

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 processes untrusted data from external sources that could contain hidden instructions.\n
  • Ingestion points: The skill explicitly requests and processes 'deal data', 'CRM exports', 'call transcripts', and 'post-mortem notes' in SKILL.md.\n
  • Boundary markers: The instructions lack clear delimiters or specific guidance for the agent to treat external data as untrusted or to ignore any instructions embedded within that data.\n
  • Capability inventory: No scripts, shell tools, or network operations are defined in this skill, although it does attempt to read context from '.agents/sales-context.md' on the local filesystem.\n
  • Sanitization: There are no provisions for sanitizing, validating, or filtering the content of the provided deal data before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 12:37 PM