doc-add-simple-hash
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted user-provided document content.
- Ingestion points: The agent reads and processes markdown documents provided in the user context.
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following directives potentially embedded within the documents.
- Capability inventory: The skill allows the agent to modify and edit document text based on the content it reads.
- Sanitization: While the skill specifies rules for the output format of hash anchors, it lacks explicit sanitization or filtering for the input text to mitigate instruction injection.
Audit Metadata