pdf-editor

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute various PDF manipulation commands via the nano-pdf CLI, such as merging, splitting, and annotating files. \n- [EXTERNAL_DOWNLOADS]: The instructions include steps to install the nano-pdf Python package from a public registry using pip or pipx. This is a necessary dependency for the skill's core functionality. \n- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by extracting text from untrusted PDF files and bringing it into the agent's context. \n
  • Ingestion points: External PDF files processed via the nano-pdf extract command in SKILL.md. \n
  • Boundary markers: None identified in the provided instructions. \n
  • Capability inventory: Bash tool for command execution, plus Read and Write for file operations as defined in the skill's frontmatter. \n
  • Sanitization: No specific sanitization or filtering of the extracted PDF text is performed before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 02:13 AM