content-amplifier
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data provided by the user, specifically transcripts, captions, or review text, to extract 'content atoms'.\n
- Ingestion points: Data enters the agent's context through user-pasted text in
references/atom-extraction.md.\n - Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions that may be hidden within the provided transcripts.\n
- Capability inventory: The skill possesses the capability to write processed results to the local file system in the
memory/directory.\n - Sanitization: No sanitization, validation, or filtering of the input text is required or specified before the extraction and virality scoring logic is applied.
Audit Metadata