datasheet-reader
Warn
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run the
pcb scancommand with user-provided arguments (local paths or URLs). This pattern creates a command injection surface if the input is not strictly sanitized before being passed to the shell. - [PROMPT_INJECTION]: The workflow involves fetching untrusted content from external URLs or local PDFs and then reading the processed output. This exposes the agent to indirect prompt injection, where a malicious document could contain instructions to override the agent's behavior.
- Ingestion points: Technical PDFs and URLs provided by users or found in files (SKILL.md).
- Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to ignore instructions embedded within the processed document.
- Capability inventory: Shell command execution via
pcb scan(SKILL.md). - Sanitization: Absent. There is no mention of input validation or escaping for the
<input>parameter before it is executed in bash.
Audit Metadata