skill-task-management
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with the version control system and manage migration tasks.
- Uses
git status,git branch,git diff,git add, andgit committo create work-in-progress checkpoints. - Invokes a vendor-provided migration script located at
"${HOME}/.claude-octopus/plugin/scripts/migrate-todos.sh"to convert legacy todo files. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could be used to influence agent behavior.
- Ingestion points: Captures user-supplied task subjects, descriptions, and dependencies. It also reads git metadata, including branch names and commit history, into the task context (SKILL.md).
- Boundary markers: The skill lacks explicit delimiters or specific instructions to the agent to disregard potentially malicious commands embedded within task descriptions.
- Capability inventory: Access to shell execution (
gitand migration scripts) and task management tools (TaskCreate,TaskUpdate,TaskList). - Sanitization: No evidence of sanitization or strict schema validation for the user-provided task content or git-derived data before it is processed by the tools.
Audit Metadata