route-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and process untrusted data from a target codebase to generate analysis reports.
  • Ingestion points: The skill reads various configuration files (package.json, requirements.txt, etc.) and codebase models based on the $ARGUMENTS variable.
  • Boundary markers: There are no instructions to use delimiters or ignore instructions found within the analyzed codebase files.
  • Capability inventory: The skill has the capability to write files to the 'docs/' directory and a hidden platform directory (~/.claude/projects/).
  • Sanitization: No sanitization or escaping mechanisms are described for the content extracted from the target codebase.
  • [DATA_EXFILTRATION]: The skill accesses a hidden directory in the user's home folder (~/.claude/projects/) to record 'Self-evolution telemetry'. Accessing hidden configuration folders associated with the agent platform can be used to harvest metadata or maintain persistence across different project contexts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — route-optimizer