repurpose-twitter
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on content transformation and does not exhibit any dangerous behaviors. It does not attempt to access sensitive files, perform unauthorized network requests, or execute arbitrary code.- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes content from untrusted sources like external URLs.
- Ingestion points: Content is ingested via the main argument specified in the
argument-hint. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands in the source text.
- Capability inventory: The skill is restricted to generating text and writing to local markdown files (
twitter/thread.md, etc.). - Sanitization: There is no evidence of input validation or sanitization for the content processed from URLs.
Audit Metadata