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-qafor 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