extract-thread-spine
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a 'published essay P', which is untrusted external content provided by a user or fetched from the web.
- Ingestion points: The skill reads an external essay (File: SKILL.md, Workflow Step 1).
- Boundary markers: The instructions do not define clear delimiters or include 'ignore embedded instructions' warnings for the input essay content.
- Capability inventory: The agent is instructed to perform file system operations, specifically writing a structured
_spine.jsonartifact (File: SKILL.md, Workflow Step 7). - Sanitization: There are no sanitization, escaping, or validation steps mentioned to prevent the agent from accidentally executing commands or following instructions that might be hidden inside the text of the essay being analyzed.
Audit Metadata