gtm-context
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting data from external or untrusted sources to create configuration files that influence other agent behaviors.
- Ingestion points: Processes content from project
README.md, documentation, and marketing sites in the auto-draft phase (Step 2). - Boundary markers: Absent; the instructions do not provide delimiters or warnings to prevent the agent from processing instructions embedded within the ingested data.
- Capability inventory: File writing to
.agents/gtm-context.md, which is a shared configuration file read by multiple other skills (e.g., email-writer, prospect-finder). - Sanitization: Absent; the skill relies on manual user review rather than implementing automated validation or filtering of the source data.
Audit Metadata