gtm-deal-pulse
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources, creating a surface for indirect prompt injection attacks where malicious instructions hidden in data could influence agent behavior.
- Ingestion points: The skill ingests CRM activity history, call transcripts, and email threads in Step 2 of the workflow (SKILL.md).
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested text are present.
- Capability inventory: The skill possesses file writing capabilities (Write tool mentioned in Artifact Generation) and potential dynamic execution via Python (Option C).
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external transcripts or emails before processing.
- [DYNAMIC_EXECUTION]: The skill provides an option to generate PDF reports using Python and the reportlab library, which involves runtime script generation.
- Evidence: SKILL.md under the 'Artifact Generation' section, specifically Option C, suggests using 'Python + reportlab' for direct PDF output.
- Context: This is categorized as low severity as it is a standard reporting function intended to produce formatted documents from analyzed data.
Audit Metadata