termination-general
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists entirely of Markdown documentation (
SKILL.mdandscripts/playbook.md). No executable scripts (Python, JavaScript, Shell) or configuration files that could trigger command execution were detected. - [Indirect Prompt Injection] (SAFE): While the skill is designed to ingest and process untrusted user data (contract clauses), it lacks any capabilities (such as file-writing, network access, or shell execution) that could be exploited via an injection attack.
- Ingestion points:
SKILL.mdStep 2 (Analysis) involves processing user-uploaded text. - Boundary markers: Absent; the skill does not explicitly define delimiters for untrusted text.
- Capability inventory: No executable capabilities or tool access found in the skill structure.
- Sanitization: Absent; the skill relies on the underlying LLM's native handling of text data.
Audit Metadata