craig-call-debrief-pl
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze sales call transcripts and notes provided by the user, creating an attack surface for instructions embedded in that data.
- Ingestion points: The skill prompts the user to provide notes or transcripts for analysis as part of the primary workflow described in
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the analytical task and potential commands embedded within the user-provided text.
- Capability inventory: The skill utilizes the agent's natural language generation to create recap emails and summaries; it does not define or request use of network-enabled tools or system-level subprocess executions.
- Sanitization: No input validation, escaping, or filtering mechanisms are defined for the transcript content before processing.
- [NO_CODE]: This skill consists entirely of instructional markdown and templates without any accompanying scripts or executables.
Audit Metadata