paperless

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE] (HIGH): The skill documentation specifies that it retrieves PAPERLESS_TOKEN and PAPERLESS_URL from ~/.secrets.env. Direct access to files containing secrets on the host system is a significant security risk for credential exposure.
  • [COMMAND_EXECUTION] (MEDIUM): The skill uses the Bash tool to execute paperless-cli. The provenance and integrity of this CLI tool are not defined in the skill package, creating a dependency on unverified external code that could perform unauthorized actions.
  • [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface (Category 8) by reading extracted text content from arbitrary documents. 1. Ingestion points: Extracted text content from documents retrieved via paperless-cli. 2. Boundary markers: Absent. 3. Capability inventory: Bash tool access, file downloads, and metadata modification. 4. Sanitization: No sanitization or safety delimiters are described for processed document text.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 18, 2026, 03:19 AM