convert-pdf
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute conversion commands. It instructs the agent to interpolate user-provided file paths (referenced as
$1) directly into shell command strings (e.g.,docling ... $1). This pattern presents a risk of command injection if the agent fails to properly escape shell metacharacters in the filenames provided by the user. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external, untrusted PDF data for LLM analysis.
- Ingestion points: External PDF files processed via the
$1argument inSKILL.md. - Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore embedded instructions when reading the converted output.
- Capability inventory: The agent has access to
Bash,Read,Write, and otherSkilltools, which could be leveraged if an injection is successful. - Sanitization: Absent. There is no evidence of filtering or sanitizing the content extracted from the PDFs before it is returned to the agent's context.
Audit Metadata