waiver-general

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill is composed entirely of Markdown documentation (SKILL.md and scripts/playbook.md). There are no scripts, binaries, or configuration files that execute code.
  • INDIRECT_PROMPT_INJECTION (SAFE): The skill's primary function is to process user-supplied contract text. While this is a theoretical entry point for indirect prompt injection, the skill lacks any capabilities (network, file system, or shell access) that could be leveraged maliciously. Analysis of the ingestion process: 1. Ingestion points: Contract text pasted or uploaded by user (referenced in SKILL.md). 2. Boundary markers: Absent; the skill does not explicitly define delimiters for the input text. 3. Capability inventory: No executable capabilities identified across any files. 4. Sanitization: Absent; the skill performs text-to-text transformation without validation, but has no destructive 'teeth'.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 11:46 AM
Security Audit — agent-trust-hub — waiver-general