summarize
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from URLs or local files and interpolates the resulting Markdown content directly into a prompt for the
pisummarization tool. - Ingestion points: The
inputargument into-markdown.mjsaccepts arbitrary URLs and file paths, loading their content into the agent's context. - Boundary markers: The summarization prompt uses
--- BEGIN DOCUMENT (Markdown) ---and--- END DOCUMENT ---delimiters to separate the document content from instructions. - Capability inventory: The skill has the ability to execute subprocesses (
uvx,pi) and write files to the local filesystem (e.g.,/tmp/pi-summarize-out/). - Sanitization: There is no evidence of sanitization or escaping of the ingested document content before it is interpolated into the summarization prompt, which could allow an attacker-controlled document to override instructions.
- [COMMAND_EXECUTION]: The
to-markdown.mjsscript useschild_process.spawnSyncto invoke external CLI tools includinguvxandpi. While the script safely uses argument arrays to prevent shell injection, it facilitates the execution of external binaries based on user-provided inputs. - [EXTERNAL_DOWNLOADS]: The skill leverages Microsoft's
markitdownutility to fetch content from remote URLs and usesuvxto dynamically install the package from PyPI during execution.
Audit Metadata