cdd-implement-todo
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is instructed to run commands found in the
Automated checkssection ofTODO.mdandTODO-*.mdfiles. This is a primary capability used to verify the correctness of the code implementations it performs. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests instructions and command sequences from external files which may be untrusted in some contexts.
- Ingestion points: The skill reads several repository files, including
TODO.md,TODO-*.md,AGENTS.md, andREADME.md(as seen inSKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from obeying malicious instructions embedded within the TODO task descriptions or check commands.
- Capability inventory: The skill possesses the capability to modify repository files (implementation and TODO updates) and execute shell commands (automated checks).
- Sanitization: There is no evidence of command validation or sanitization before the execution of the automated checks extracted from the files.
Audit Metadata