resume-work
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external and potentially untrusted sources such as Git commit histories, issue trackers, and local file pointers. Malicious content embedded in these sources could attempt to override agent instructions. The skill includes a mitigation strategy by explicitly instructing the agent to treat these 'capsules' as claims to verify rather than memory to trust blindly.- [COMMAND_EXECUTION]: The skill invokes a local CLI tool (
node .agents/universal-agent-skills/runtime/cli.mjs) to perform reconciliation and resume operations. This executable is a functional component of the skill and operates on local paths defined within the agent's environment.
Audit Metadata