dl-execute
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external files such as implementation specifications, test-driven development configurations, and bug diagnosis reports. This ingestion surface could be exploited if these files contain hidden instructions intended to hijack the agent's logic.
- Ingestion points: SKILL.md specifies that the agent should read 'implement-spec', 'tdd', and 'diagnosing-bugs' files from the project environment.
- Boundary markers: The instructions do not define delimiters or explicit warnings for the agent to ignore instructions embedded within the processed data.
- Capability inventory: The skill manages git worktrees, creates integration branches, and executes test suites.
- Sanitization: There are no defined mechanisms for sanitizing or validating the content of external files before the agent acts upon them.
- [COMMAND_EXECUTION]: The skill performs command-line operations for git version control management and test execution. While these are necessary for the skill's stated purpose, they provide the functional capacity for an injection attack to affect the local environment.
Audit Metadata