work-summary
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as 'git log' and 'find' to analyze project history and identify file changes. These commands are used as intended for work summary generation within the local project scope.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the ingestion of external data from the project's environment. \n
- Ingestion points: It reads data from git commit messages and file contents within specific directories like 'src/' and 'skills/'. \n
- Boundary markers: None. The skill does not define delimiters or provide instructions to the agent to ignore potentially malicious instructions embedded in the commit history or source files. \n
- Capability inventory: The skill possesses capabilities for shell command execution (git, find), file reading, and file writing (to 'src/docs/'). \n
- Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed and outputted in the summary.
Audit Metadata