creator-clarify

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely composed of markdown instructions and does not contain any executable scripts, shell commands, or binary files. It explicitly defines a non-mutation rule that prevents the creation or modification of goals, projects, or issues within the managed organization.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it can ingest external content from a Paperclip wiki via the paperclip-wiki-fetch tool (SKILL.md). 1. Ingestion points: Operator-provided wiki URLs or content processed by the wiki-fetch tool. 2. Boundary markers: None present in the instructions. 3. Capability inventory: The skill is strictly non-mutating and lacks file system access, network exfiltration, or code execution capabilities. 4. Sanitization: No sanitization or filtering of the ingested wiki content is specified. Despite the absence of delimiters, the risk is safe due to the skill's lack of exploitable capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:15 PM
Security Audit — agent-trust-hub — creator-clarify