proof-reading
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill body and metadata reveals no malicious code, hidden commands, or suspicious scripts. The skill is entirely prompt-driven.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted user text. 1. Ingestion points: Written content provided by the user as specified in SKILL.md. 2. Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the prompt instructions. 3. Capability inventory: No subprocess calls, network operations, or file-write operations are found across all files. 4. Sanitization: No sanitization or filtering of external content is implemented. However, the overall risk is safe as the agent lacks any dangerous tools that could be exploited via injection.
Audit Metadata