accessibility
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The 'Memory Protocol' section in
SKILL.mdinstructs the agent to use thecatcommand to read internal project memory stored in.claude/context/memory/learnings.md. - [PROMPT_INJECTION]: The skill ingests untrusted code from the
src/directory, establishing a vulnerability surface for indirect prompt injection where malicious content in source files could influence agent behavior. - Ingestion points: Source files targeted by the
src/**/*.*glob inSKILL.md. - Boundary markers: No delimiters or ignore instructions are provided for processed data.
- Capability inventory: The skill utilizes
Read,Write, andEditcapabilities. - Sanitization: No sanitization or validation of external content is performed.
Audit Metadata