word-proofreader
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from user-provided Word documents, creating a surface for indirect prompt injection where a malicious document could attempt to influence the agent's behavior.
- Ingestion points: The
proofreader.pyscript (line 34) extracts raw text from document paragraphs and provides it to the agent for analysis. - Boundary markers: There are no explicit delimiters or instructions provided in the
SKILL.mdworkflow to separate document content from processing instructions, nor are there warnings to ignore embedded commands. - Capability inventory: The skill is capable of executing a local Python script and performing file system writes when saving corrected documents.
- Sanitization: The extracted text is passed directly to the agent without filtering or sanitization of potential instruction-like strings.
Audit Metadata