threads-growth
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could lead to indirect prompt injection. Malicious instructions embedded in brand profiles or goal documents could influence the agent's output during content drafting.
- Ingestion points: The skill explicitly reads 'brand-profile' and 'goals-and-kpis' files as context (SKILL.md).
- Boundary markers: There are no explicit instructions to the agent to ignore or delimit embedded instructions within the ingested files.
- Capability inventory: The agent can draft original posts and suggested replies, and interface with the WoopSocial tool for publication (SKILL.md, scope-and-connections.md).
- Sanitization: The skill does not implement validation or sanitization routines for the data read from external profiles.
Audit Metadata