modern-drug-rehab-computer

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill includes WebFetch and WebSearch tools that establish a surface for indirect prompt injection. 1. Ingestion points: Data from untrusted external websites can enter the agent context through these web tools. 2. Boundary markers: The skill instructions lack delimiters or specific warnings to prevent the agent from following instructions embedded in retrieved external data. 3. Capability inventory: The agent has permissions to read, write, and edit files, and use web tools. 4. Sanitization: No logic is provided to sanitize or validate external content before processing.
  • [NO_CODE]: The skill is composed entirely of informational markdown documentation and does not include any scripts, binaries, or configuration files for external software dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:26 PM