timeless-docs
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes documentation and source code from the local environment without using boundary markers to isolate instructions from data.\n
- Ingestion points: Processes content from
git diff,git status, and file read operations as described in the "Scope: two modes" section.\n - Boundary markers: Lacks explicit delimiters or instructions for the agent to ignore instructions embedded within the processed documentation.\n
- Capability inventory: The skill possesses capabilities to read and write to the filesystem and execute shell-based tools (
git,grep).\n - Sanitization: No sanitization or validation logic is defined for the content retrieved from local files before it is processed by the model.\n- [COMMAND_EXECUTION]: The skill uses shell commands to identify and scan files for cleanup candidates.\n
- Evidence: Instructions include the use of
git status --porcelain,git diff, andgrep -rniEto discover target documentation and comments.
Audit Metadata