skills/decocms/mcps/generate-report/Gen Agent Trust Hub

generate-report

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a Git workflow using shell commands (git checkout, commit, push) to manage reports on a specialized repository branch.
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified where the skill ingests untrusted repository data.
  • Ingestion points: The skill analyses repository code, data, and context to populate report fields (SKILL.md).
  • Boundary markers: No delimiters or instructions are provided to help the agent distinguish between data to be analyzed and instructions within that data.
  • Capability inventory: The skill uses file-writing capabilities and Git push commands to persist generated reports (SKILL.md).
  • Sanitization: No content validation or escaping is specified for data extracted from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 12:43 AM
Security Audit — agent-trust-hub — generate-report