string-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and process arbitrary text strings from the codebase, including error messages and UI text. This represents a potential surface for indirect prompt injection if those strings contain instructions meant to influence the agent's behavior. However, the risk is minimized by the skill's specific instructions to only suggest changes for human review rather than executing them directly.
- Ingestion points: Processes user-facing strings and configuration files like
packages/cli/src/config/settingsSchema.ts(referenced inSKILL.md). - Boundary markers: The instructions do not specify specific delimiters for the strings being reviewed, though they mandate a strict output format for suggestions.
- Capability inventory: The skill is limited to text analysis and providing suggestions. It does not utilize capabilities for file writing, network communication, or subprocess execution.
- Sanitization: No explicit sanitization of codebase strings is performed; the skill relies on a human-in-the-loop process for final approval.
Audit Metadata