binlee-compliance-risk
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a potential attack surface for indirect prompt injection through its document processing workflow.\n
- Ingestion points: The skill reads and evaluates content from
../binlee-source-library/references/evidence-policy.mdand related corpora.\n - Boundary markers: There are no instructions or delimiters defining the start and end of untrusted data to prevent the agent from executing instructions found within the files.\n
- Capability inventory: The skill's capabilities are limited to text processing and analysis; it does not request network access or shell command execution.\n
- Sanitization: No sanitization or filtering logic is present to validate the content of the external files being processed.
Audit Metadata