ln-511-code-quality-checker
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core workflow involves ingesting and analyzing untrusted data from external sources. Malicious instructions placed in story descriptions or source code comments could attempt to manipulate the agent's analysis or bypass quality scores.
- Ingestion points: Linear stories, implementation task descriptions, and project source files.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating untrusted data into the agent context.
- Capability inventory: The agent has access to shell commands (Bash), file system tools (Read, Glob, Grep), and network capabilities for research (WebFetch, mcp__Ref).
- Sanitization: No explicit sanitization or filtering logic is defined for the content retrieved from Linear or the local codebase before it is processed by the agent.
Audit Metadata