hubspot-implementation-plan
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) andgitto manage repository forks and pull requests for community contributions. Commands identified includegh repo fork tomgranot/hubspot-admin-skills --clone,git push, andgh pr create.- [PROMPT_INJECTION]: The skill reads and processes audit findings from external files in thereports/directory to generate implementation steps. This represents an indirect prompt injection surface where malicious instructions in a report could influence agent behavior. - Ingestion points:
reports/hubspot-audit-*.md(Step 1) - Boundary markers: None identified in the instruction logic.
- Capability inventory: Shell execution (git, gh), file system writes (writing new plan reports), and potential creation of new skill files.
- Sanitization: No explicit validation or sanitization of audit report content is described.- [COMMAND_EXECUTION]: The skill includes instructions to dynamically generate new
SKILL.mdfiles to address gaps found in audits. This involves writing executable agent instructions to the local file system and potentially pushing them to remote repositories.
Audit Metadata