archive
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled feature files, proposals, and design documents which are then parsed and synced to long-term documentation.
- Ingestion points: The skill reads feature files, proposals, and design documents from the change directory in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are present in the processing logic.
- Capability inventory: The skill performs file system operations including
mkdirandmv, and writes data tobeat/CONTEXT.mdand capability-specificREADME.mdfiles. - Sanitization: There is no evidence of content sanitization or validation before the data is integrated into the living documentation.
- [COMMAND_EXECUTION]: The skill executes shell commands for directory management and file organization during the archiving process.
- Evidence: The skill uses
mkdir -p beat/changes/archiveandmv beat/changes/<name> beat/changes/archive/YYYY-MM-DD-<name>to handle directory movement as part of its terminal state logic inSKILL.md. These operations are consistent with the skill's primary purpose.
Audit Metadata