performance-review-self-assessment
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses local directory names to identify team members and performs file-write operations to save sensitive performance assessments.
- Evidence: In
SKILL.md, the agent is instructed to look up subdirectories in a quarter folder (e.g.,Q12026/) to list team members and save a markdown file to<quarter>/<person>/sources/. - [INDIRECT_PROMPT_INJECTION]: The skill ingests directory names from the local workspace as data, creating a surface where maliciously crafted directory names could influence agent behavior.
- Ingestion points: Subdirectory names in the quarter folder are used to populate the team member list in
SKILL.md(Step 1). - Boundary markers: No explicit boundary markers or instructions are provided to the agent to disregard potential instructions embedded in directory names.
- Capability inventory: The skill has the capability to list directories and write files to the local disk.
- Sanitization: There is no evidence of sanitization or validation performed on the directory names before they are presented to the user.
Audit Metadata