skills/howells/fiction/status/Gen Agent Trust Hub

status

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, network exfiltration, or credential access were identified in the instructions.
  • [NO_CODE]: The skill contains no scripts, binaries, or dependencies, consisting solely of markdown instructions.
  • [PROMPT_INJECTION]: The skill processes untrusted local data, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Project README, character docs, and world docs described in SKILL.md.
  • Boundary markers: No delimiters or isolation instructions are provided for file content.
  • Capability inventory: No tools or shell commands are defined in the skill files.
  • Sanitization: The skill does not include instructions to sanitize or validate the content of the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 05:14 AM
Security Audit — agent-trust-hub — status