skills/szoloth/skill-pack/napkin/Gen Agent Trust Hub

napkin

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by mandating that the agent read and silently internalize instructions from .claude/napkin.md at the beginning of every session.\n
  • Ingestion points: The file .claude/napkin.md within the repository serves as the primary ingestion point for untrusted data.\n
  • Boundary markers: Absent. The skill provides no delimiters or instructions to treat the content of the runbook as untrusted; instead, it explicitly tells the agent to "apply it silently."\n
  • Capability inventory: The agent's existing capabilities (such as filesystem access and terminal execution) provide a target for malicious instructions stored in the napkin file.\n
  • Sanitization: Absent. There are no mechanisms described for validating, escaping, or filtering the data read from the napkin file before it influences agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 09:47 PM
Security Audit — agent-trust-hub — napkin