customer-call-to-product-work

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands using the monologue utility (e.g., monologue notes all --q "...", monologue notes get NOTE_ID). These commands are used to search and retrieve customer call data for analysis.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it processes untrusted data from external sources.
  • Ingestion points: Customer call transcripts and notes are retrieved via the monologue tool and ingested into the agent context.
  • Boundary markers: The instructions lack explicit boundary markers or delimiters (e.g., XML tags or triple backticks with 'ignore' instructions) when processing the transcript content.
  • Capability inventory: The skill operates in an environment where the agent may have the ability to create issues, edit code, or communicate with customers, although these actions are gated by a requirement for explicit user authorization.
  • Sanitization: There is no evidence of content sanitization or validation performed on the retrieved transcripts before they are analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 07:03 AM
Security Audit — agent-trust-hub — customer-call-to-product-work