church-ship

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a CLI tool named 'church' to perform various repository-related tasks, including loading context, checking ledgers, and advancing the lifecycle status of a project.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data like code diffs and PR descriptions.
  • Ingestion points: External data enters the agent context through the processing of PR diffs and UAT results specified in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the diffs or UAT results.
  • Capability inventory: The agent can execute system commands via the 'church' CLI tool, as seen in the bash snippets in SKILL.md.
  • Sanitization: The instructions do not define any sanitization or validation steps for the input data before it is evaluated by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 04:40 PM
Security Audit — agent-trust-hub — church-ship