tidy
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
tidy.py,wiki-health.py) and git commands (git mv,git status) to manage file archiving and indexing. These commands are triggered based on the status of documentation files. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from local markdown (
.md) and HTML files to determine which pieces of information should be "promoted" to the wiki. This creates an attack surface where instructions embedded in those files could influence the agent's behavior. - Ingestion points: The agent reads the content and frontmatter of files in
wiki/sources/draft/*.mdandllmwiki/html/*.htmlto evaluate them for archiving or promotion. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious embedded instructions within the files being processed.
- Capability inventory: The skill has the capability to execute Python scripts, move files using
git mv, and write new documentation files (ADRs and concepts) to the local filesystem. - Sanitization: No content sanitization or validation of the draft contents is mentioned before the agent processes and acts upon the data.
Audit Metadata