grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it directs the agent to read and follow context from external, potentially untrusted sources like source code and configuration files.
  • Ingestion points: Source files, types, configurations, and existing implementations (SKILL.md).
  • Boundary markers: None present; there are no instructions to ignore embedded commands or treat file content as data only.
  • Capability inventory: The skill utilizes the agent's inherent file-read capabilities to inspect the codebase.
  • Sanitization: No sanitization or validation logic is defined to protect against malicious instructions embedded in comments or configuration values.
  • [NO_CODE]: The skill contains no executable code, scripts, or package dependencies, relying entirely on the agent's internal reasoning and standard tools.
  • Evidence: The skill definition is restricted to a markdown file with natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 07:58 AM