writing-beats
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted markdown data from user-provided files to generate article content, establishing a standard surface for indirect instructions.
- Ingestion points: Raw material markdown files provided by the user as described in SKILL.md.
- Boundary markers: Absent; instructions do not provide specific delimiters or warnings to isolate embedded content.
- Capability inventory: The skill performs local file read and write operations to manage content development.
- Sanitization: Absent; the prompt does not describe any validation or filtering of the raw material before processing.
Audit Metadata