swipe-file-generator
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- Indirect Prompt Injection (HIGH): The skill fetches and processes content from arbitrary external URLs and passes this untrusted data to a subagent for analysis. This creates a significant attack surface for indirect prompt injection.
- Ingestion points:
SKILL.mdfetches content from user-provided URLs andapi.fxtwitter.com(Step 3). - Boundary markers: Partial. The skill uses
--- Content X ---delimiters when passing content to the subagent, which provides weak protection against adversarial content. - Capability inventory: The agent has file write capabilities (
/swipe-file/swipe-file.md) and network access viaWebFetch. - Sanitization: Absent. No filtering or escaping is performed on the fetched content before it is processed by the LLM.
- Data Exposure & Exfiltration (LOW): The skill performs network requests to non-whitelisted domains, including
api.fxtwitter.com. While this is functional for the skill's purpose, it involves sending URL metadata to a third-party service.
Recommendations
- AI detected serious security threats
Audit Metadata