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

grill-me

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather facts from external sources like the filesystem, code, tools, and the web, creating a potential surface where instructions embedded in those sources could influence the agent's behavior during the interview rounds. Ingestion points: External facts retrieved from the filesystem, code, tools, documentation, and the web as described in SKILL.md. Boundary markers: Absent; the instructions do not define delimiters for this external content. Capability inventory: The skill utilizes subagents to read and process environment data (SKILL.md). Sanitization: Absent; no validation of the retrieved facts is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill contains a reference to an external GitHub repository in ATTRIBUTION.md for attribution purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:10 PM
Security Audit — agent-trust-hub — grill-me