invoice-generator
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to discover repositories and extract commit logs.
- Evidence: Shell loops used to identify directories containing
.gitfolders. - Evidence: Execution of
git logwith parameters for author, date range, and formatting. - Evidence: Retrieval of the current git user name via
git config user.name. - [INDIRECT_PROMPT_INJECTION]: The skill processes git commit messages which are external and potentially untrusted data sources. This creates a surface where malicious commit messages could attempt to override the summarization rules or influence the behavior of the downstream
management-talkskill. - Ingestion points: Git commit messages extracted via
git logacross all workspace repositories. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded within commit messages.
- Capability inventory: The agent has the ability to execute shell commands (
git,bash) and invoke other skills (dev-workflows:management-talk). - Sanitization: No specific sanitization or filtering of commit content is mentioned before the data is passed to the summarization logic or the next skill.
Audit Metadata