skills/tw93/waza/read/Gen Agent Trust Hub

read

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web pages and document content, presenting an indirect prompt injection surface.\n
  • Ingestion points: Arbitrary URLs and PDF documents ingested via scripts/fetch.sh, scripts/fetch_local.py, scripts/fetch_feishu.py, and scripts/fetch_weixin.py.\n
  • Boundary markers: Present. SKILL.md contains strict rules instructing the agent to treat all fetched content as untrusted data and ignore embedded overrides, urgency appeals, or role reassignments.\n
  • Capability inventory: The skill executes local bash and python helper scripts, downloads images, and writes output to local session directories.\n
  • Sanitization: Standard HTML parsing and text extraction are performed, but raw extracted text is passed to the model context, relying on the model's adherence to safety guidelines.\n- [COMMAND_EXECUTION]: Command templates defined in references/read-methods.md interpolate user-controlled variables such as {url}, {user}, and {repo} into shell commands. If the agent executes these directly via a shell wrapper without proper escaping, it could lead to command injection if a user supplies a malicious URL with shell metacharacters.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:24 PM
Security Audit — agent-trust-hub — read