writing-beats

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external content provided by the user. 1. Ingestion points: Content from a user-supplied markdown file of 'raw material'. 2. Boundary markers: Absent; the skill does not define delimiters or instructions to ignore commands within the raw material. 3. Capability inventory: Reading and writing to markdown files on the local filesystem. 4. Sanitization: Absent; no validation or sanitization of the input material is performed.
  • [NO_CODE]: The skill is comprised entirely of instructions and metadata. It does not include any scripts, binary files, or external software dependencies, which limits its direct exploitability.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:26 PM
Security Audit — agent-trust-hub — writing-beats