summarization

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its core functionality of processing untrusted external data.
  • Ingestion points: The skill explicitly uses the Read tool for local files/directories and the WebFetch tool for arbitrary remote URLs provided by users.
  • Boundary markers: The workflow lacks instructions to use boundary markers (like XML tags or delimiters) or explicit 'ignore embedded instructions' warnings when processing retrieved content.
  • Capability inventory: The agent is granted capabilities to perform file system discovery (Glob), file reading (Read), and network retrieval (WebFetch).
  • Sanitization: No sanitization, validation, or escaping logic is defined for the content before it is interpolated into the summarization prompt.
  • [NO_CODE]: This skill contains no executable scripts (Python, JavaScript, etc.) or binary files. It consists entirely of markdown-based instructions for the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:16 AM