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) and git to manage repository forks and pull requests for community contributions. Commands identified include gh repo fork tomgranot/hubspot-admin-skills --clone, git push, and gh pr create.- [PROMPT_INJECTION]: The skill reads and processes audit findings from external files in the reports/ 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.md files 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
Risk Level
SAFE
Analyzed
Apr 9, 2026, 04:20 AM