qodo-get-relevant-rules

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses the user's home directory to read ~/.qodo/config.json for an API key and configuration settings. These credentials are transmitted via the Authorization header to the official Qodo API (qodo-platform.qodo.ai) to authenticate rule search requests.\n- [PROMPT_INJECTION]: The skill implements a feature where rules fetched from an external API are incorporated into the agent's context to guide code generation. This creates a surface for indirect prompt injection (tool output poisoning), although the risk is mitigated by the use of a trusted vendor API.\n- [COMMAND_EXECUTION]: The skill performs shell operations using Bash to verify the git repository status (git rev-parse) and generate unique request identifiers using a Python one-liner (python3 -c). These commands are standard for the skill's operational logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 06:30 PM