writing-style-and-tone
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process text drafts provided by users or other AI agents, creating a surface for indirect prompt injection where malicious instructions could be embedded in the data being styled.
- Ingestion points: The skill processes external drafts as described in
SKILL.md("Consumes: drafts from any content skill or AI assistant") andreferences/scope-and-connections.md. - Boundary markers: There are no explicit instructions to use delimiters or "ignore embedded instructions" warnings when the agent interpolates or processes the external drafts.
- Capability inventory: The skill instructions involve connecting to a publishing workflow via
WoopSocial, as noted inSKILL.mdandreferences/scope-and-connections.md. - Sanitization: No sanitization, escaping, or filtering of the ingested content is specified in the edit passes.
- Mitigation: The risk is lowered by the "Honest scope" requirement that a human must supply lived specifics and give the final approval before any content is published.
Audit Metadata