afk-implement
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses several CLI utilities to automate and track the implementation process.\n
- Evidence: The instructions in SKILL.md direct the agent to use 'git' for version control, 'yggtree' for managing implementation worktrees, 'afk-code-review' for automated code audits, and 'plannotator' for reviewing changes and implementation records. These tools are used for their intended purposes within the implementation and review lifecycle.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which may contain hidden or malicious instructions.\n
- Ingestion points: The agent is instructed to read all sources provided by the user, such as tickets, specifications, plans, and prototypes, to shape the implementation.\n
- Boundary markers: The skill does not provide instructions to use delimiters or specific ignore-rules when processing content from these external sources.\n
- Capability inventory: The agent has the ability to execute shell commands via the implementation tools and write files to the local repository (records, ADRs, and source code).\n
- Sanitization: No sanitization or validation of the input content from external sources is described in the workflow.
Audit Metadata