gtm-brief
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's 'UPDATE' mode involves reading existing GTM briefs, which creates a vulnerability surface where adversarial instructions embedded in those documents could potentially influence the agent's actions during the modification process.
- Ingestion points: The skill reads existing files from the
gtm/,launch/,marketing/, andbriefs/directories to facilitate updates or searches as defined in the 'Mode Behaviors' and 'Search Locations' sections of SKILL.md. - Boundary markers: Absent. The instructions do not define specific delimiters or provide the agent with 'ignore embedded instructions' warnings when processing the content of retrieved files.
- Capability inventory: The skill possesses the capability to read and write files within the local filesystem to manage the GTM document lifecycle.
- Sanitization: Absent. There is no evidence of content validation, filtering, or escaping applied to the data read from existing briefs before it is interpolated into the agent's context for updates.
Audit Metadata