skills/marclelamy/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is instructed to 'explore the codebase' to answer questions. This behavior creates a surface where the agent might encounter and follow malicious instructions embedded in the project files it analyzes.
  • Ingestion points: Codebase files (referenced in SKILL.md prompt).
  • Boundary markers: Absent; there are no instructions to ignore embedded commands within the files.
  • Capability inventory: File system read tools used for codebase exploration.
  • Sanitization: Absent; the skill does not specify validation for content read from the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:53 PM
Security Audit — agent-trust-hub — grill-me