threads-repurposer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content from external platforms (LinkedIn, X, YouTube, blogs). This creates an attack surface where instructions embedded in the source text could attempt to influence the agent's behavior.
- Ingestion points: The agent accepts source text or links provided by the user in the first step of the workflow.
- Boundary markers: The instructions do not explicitly define delimiters for the source content, though the transformation process (extracting the 'spine') naturally isolates the core message.
- Capability inventory: The skill can read local reference files and use the
lib.publishtool to send data to Threads. - Sanitization: The skill includes a 'humanizer pass' and a cleaning phase to strip off-platform artifacts, which transforms the input. Crucially, Step 9 requires an 'Approval card' where the user must review and confirm the content before the publishing tool is invoked in Step 10, providing a significant manual safety check.
Audit Metadata