scrolls-compact
Pass
Audited by Gen Agent Trust Hub on Nov 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on local
gitcommand execution to function. - The core logic in
scripts/compact.pyusessubprocess.runto execute commands likegit blame,git rev-parse,git show,git commit, andgit tag. - These operations are used to identify the age of content and manage the checkpointing process. Commands are constructed using lists (avoiding shell interpolation) and target local repository data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from documentation files that may contain untrusted data.
- Ingestion points: Reads files like
SPEC.md,PLAN.md, andHANDOFF.mdfrom the project directory (specified inSKILL.md). - Boundary markers: Absent. The skill reads raw Markdown content without delimiters separating data from instructions.
- Capability inventory: The skill has the capability to write to the local filesystem and perform git commits/tags.
- Sanitization: The
--finalizemode performs validation to ensure only designated "old" units were modified, providing a safeguard against unintended edits by the agent. - [EXTERNAL_DOWNLOADS]: The skill references an external resource for its maintenance components.
- The maintenance script
scripts/build_example_viewer.pyand the resultingassets/example-viewer.htmlreference themarkedlibrary fromcdnjs.cloudflare.com. - This resource is fetched from a well-known service and is used only for rendering documentation examples in a browser.
Audit Metadata