vueuse-library-rule
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it processes untrusted data from the source directory using powerful file-modification tools.\n
- Ingestion points: The skill reads all project files matching the glob
src/**/*.*.\n - Boundary markers: No delimiters or explicit instructions are provided to distinguish between the agent's instructions and potentially malicious content within the source files.\n
- Capability inventory: The agent has access to
Read,Write, andEdittools, allowing it to modify the file system if it inadvertently follows instructions embedded in source code.\n - Sanitization: There is no sanitization or validation of the file contents before they are processed by the LLM.\n- COMMAND_EXECUTION (LOW): The skill's 'Memory Protocol' contains a hardcoded instruction to execute a shell command to manage its internal state.\n
- Evidence: The instruction
cat .claude/context/memory/learnings.mdis present in the SKILL.md file.\n - Context: While this is a command execution pattern, its impact is limited to reading a specific, local, non-sensitive configuration file used for persistence in certain agent environments.
Audit Metadata