review-prd
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts
parse_docs.pyandgenerate_report.pyvia the command line to handle document conversion and report generation. This is a standard and documented part of the skill's workflow. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external documents.
- Ingestion points: The skill reads content from
.docx,.xlsx, and.mdfiles provided by the user in a specified directory. - Boundary markers: No specific delimiters or "ignore instructions" warnings are used to separate the document content from the agent's instructions.
- Capability inventory: The skill has the capability to execute shell commands (
python) and write files to the local filesystem via the provided scripts. - Sanitization: There is no evidence of sanitization or filtering of the text extracted from the documents before it is processed by the AI.
Audit Metadata