performance-review
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of rough notes or bullet points to generate structured performance reviews. This creates a surface for indirect prompt injection, where malicious instructions could be hidden in the input notes to influence the AI output.
- Ingestion points: User-provided notes processed via instructions in SKILL.md.
- Boundary markers: Absent; the skill does not use delimiters or specific instructions to isolate user input from its own instructional context.
- Capability inventory: The skill has no tool-using capabilities, such as network access, file system modifications, or subprocess execution.
- Sanitization: No sanitization or validation of the input content is performed to detect or filter potential injection patterns.
Audit Metadata