iyeque-pdf-reader
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data from external PDF files, providing a surface for indirect prompt injection attacks. \n
- Ingestion points: The extract and metadata tools read content from the filesystem via the user-supplied file_path parameter in SKILL.md. \n
- Boundary markers: Absent. The documentation does not specify the use of delimiters or instructions for the agent to ignore any embedded prompts within the extracted text. \n
- Capability inventory: The skill executes a local Python script skills/pdf-reader/reader.py which extracts content and passes it directly to the agent's context. \n
- Sanitization: Absent. There is no evidence of sanitization, filtering, or validation of the extracted document content.\n- [COMMAND_EXECUTION]: The skill documentation illustrates the agent executing a shell command to run a local Python script (reader.py). This is the primary mechanism for the skill's functionality.
Audit Metadata