act-as-author
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and adopt the persona of the 'author' of uncommitted and unstaged changes in the current git branch. Since this external content is processed as part of the agent's context, it could contain malicious instructions or hidden prompts designed to manipulate the agent's behavior.
- Ingestion points: Unstaged and uncommitted code changes on the current branch (SKILL.md).
- Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the code changes.
- Capability inventory: The skill has the capability to propose and perform code modifications ('make changes', 'propose fixes') and likely uses git tools for branch analysis.
- Sanitization: Absent. There is no mention of filtering or validating the content of the code changes before the agent analyzes them.
Audit Metadata