gtm-context-bootstrap
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill facilitates Go-To-Market research using structured frameworks like 'Obviously Awesome' and 'Jobs to Be Done'. It does not contain malicious code or instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface for user-supplied GTM artifacts.
- Ingestion points: User's approved public materials and supplied internal source artifacts (SKILL.md).
- Boundary markers: Instructions explicitly require labeling claims as verified, owner-confirmed, assumption, or contradicted, and maintaining distinct customer language.
- Capability inventory: Reading files, writing markdown artifacts, and executing the local validation script
scripts/check-output.py. - Sanitization: Logical sanitization is enforced through source attribution and evidence-backed claims.
- [DYNAMIC_EXECUTION]: The skill utilizes a local Python script
scripts/check-output.pyto validate output completeness. The script is benign, performs only local regex-based validation, and does not exhibit dangerous behaviors like network access or unsafe deserialization. - [COMMAND_EXECUTION]: The skill instructs the agent to run a local Python validator. This is a standard and safe use of command execution for verifying artifact quality.
Audit Metadata