gtm-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files (
gtm-context.md,gtm-tracking-plan.json,gtm-implementation-log.json,gtm-test-results.json) to populate documentation templates, creating a risk surface.\n - Ingestion points: SKILL.md (Phase 0 and Phase 1) instructs the agent to read business context and implementation details from the project root.\n
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the ingested content.\n
- Capability inventory: The skill is capable of writing multiple documentation files to the file system (Phase 6).\n
- Sanitization: The instructions do not define any sanitization or validation of the input data before it is interpolated into documentation.
Audit Metadata