threads-viral-growth
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves the ingestion and analysis of untrusted data from external social media platforms, websites, and community forums (e.g., PTT, Dcard). This establishes an indirect prompt injection surface where instructions hidden within analyzed content could potentially influence the agent's output.\n
- Ingestion points:
references/01-trend-research.md(Workflow for reading Threads posts, search results, and competitor content).\n - Boundary markers: Absent; the instructions do not explicitly mandate delimiters or warnings to ignore instructions embedded in the analyzed data.\n
- Capability inventory: The skill is primarily instructional and does not invoke subprocesses, file-system writes, or sensitive network operations beyond standard browsing.\n
- Sanitization: Not present; the agent is expected to synthesize the external information directly into creative copy.
Audit Metadata