stop-me-init
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository to generate a configuration file, creating a risk that malicious instructions within those files could influence the agent's behavior.
- Ingestion points: Repository history via
git log, configuration files (Dockerfile,fly.toml,Procfile,compose,k8s manifests), CI workflows, and package manifests (package.json,pyproject.toml). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading these external files.
- Capability inventory: The skill has the capability to write the
.stop-me.ymlfile to the repository root. - Sanitization: No explicit sanitization or validation of the ingested content is mentioned before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill executes local shell commands to analyze the repository environment.
- Evidence: Instructions require running
git logandgit log --format=%ae | sort -uto determine repository age and contributor count.
Audit Metadata