performance-review-writer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which may contain hidden malicious instructions.
  • Ingestion points: The skill ingests data from emails, chat messages, and meeting threads via the WorkIQ tool (SKILL.md, Step 2).
  • Boundary markers: The instructions do not define clear boundaries or specify that the agent should ignore instructions embedded within the processed communications.
  • Capability inventory: The skill has the ability to write files to the workspace (SKILL.md, Step 4).
  • Sanitization: The skill contains instructions to redact personal details but lacks mechanisms to filter or sanitize potential prompt injection attacks contained within ingested messages.
  • [COMMAND_EXECUTION]: The skill performs automated file system operations.
  • Evidence: The skill is instructed to save final drafts to the workspace using a specific date-based folder convention (SKILL.md, Step 4).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:18 PM
Security Audit — agent-trust-hub — performance-review-writer