lyra
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text through the $ARGUMENTS variable in SKILL.md to perform optimization. This creates an attack surface for indirect prompt injection. 1. Ingestion points: The skill parses user input from the command arguments in SKILL.md. 2. Boundary markers: The instructions do not define explicit boundary markers or delimiters for the user-supplied prompt. 3. Capability inventory: The skill uses WebSearch, AskUserQuestion, Read, and Glob tools. 4. Sanitization: No explicit sanitization or filtering of the user input is mentioned in the instructions.
- [SAFE]: All tool usage is consistent with the skill's primary purpose. The use of WebSearch is restricted to finding prompt best practices, and the Read/Glob tools are used to access internal documentation files. No credentials, persistence mechanisms, or obfuscated URLs were detected during analysis.
Audit Metadata