frontend-expert
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a 'Memory Protocol' that instructs the agent to read historical data from a specific local path at startup.
- Ingestion points: The agent is directed to read from
.claude/context/memory/learnings.mdin the SKILL.md file. - Boundary markers: There are no instructions or delimiters provided to ensure the agent treats the content of the memory file as data rather than new instructions.
- Capability inventory: The skill uses a powerful toolset including
Bash,Write,Edit, andRead, which could be misused if malicious instructions are present in the ingested data. - Sanitization: The skill provides no mechanism to sanitize or validate the content of the memory file before it is processed by the agent.
Audit Metadata