jurisdiction-format
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the way it processes external patent documentation files.
- Ingestion points: The skill reads untrusted input from 'patent/CLAIMS.md', the 'patent/specification/' directory, and 'patent/INVENTION_DISCLOSURE.md'.
- Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to disregard instructions that might be embedded within the patent text.
- Capability inventory: The skill grants the agent extensive capabilities, including 'Bash', 'Read', 'Write', 'Edit', 'Grep', and 'Glob', which can be misused if an attacker embeds malicious directives in the patent files.
- Sanitization: Absent. There is no evidence of validation, escaping, or filtering of the content extracted from the input files before it is processed or written to output documents.
Audit Metadata