Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection when processing external PDF files.
- Ingestion points: Scripts like
extract_form_field_info.pyandfill_fillable_fields.pyread PDF content directly into the agent context. - Boundary markers: Absent. There are no delimiters or instructions provided to the agent to treat extracted PDF content as potentially untrusted.
- Capability inventory: The skill can create and modify files, and the documentation suggests the execution of system CLI tools.
- Sanitization: Extracted text is not sanitized or validated before being used by the agent.
Audit Metadata