asb-carol-inciting-events

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files which serves as a potential attack surface for indirect prompt injection.
  • Ingestion points: Reads from KEYSTONES.md, customer-interview findings reports, per-interview debrief files, and survey exports.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the processed data.
  • Capability inventory: The skill performs file system write operations (creating and updating INCITING-EVENTS.md) and invokes other agent skills (asb-rude-qa, asb-carol-keystones, asb-carol-define, asb-interview-goals).
  • Sanitization: There is no mention of sanitizing, escaping, or validating the content extracted from the interview artifacts before processing or writing to the output file.- [COMMAND_EXECUTION]: The skill instructions include the invocation of other specialized skills (e.g., asb-rude-qa for devil's advocate interrogation). These are identified as vendor-owned resources from the same author (asmartbear) and constitute intended cross-skill integration rather than unauthorized command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:31 PM
Security Audit — agent-trust-hub — asb-carol-inciting-events