social-crosspost
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture involves processing external data from URLs and user input, which creates a surface for indirect prompt injection.
- Ingestion points: The workflow in SKILL.md describes fetching content from user-provided URLs and reading pasted text.
- Boundary markers: The instructions do not specify using delimiters or XML tags to isolate external content from the prompt instructions.
- Capability inventory: The skill is limited to reading local files and fetching web content, lacking higher-risk permissions such as file-writing or shell execution.
- Sanitization: There are no explicit instructions for the agent to sanitize or ignore instructions embedded within the source material.
Audit Metadata