todo-resolve

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs file system management, including creating scratch directories at .context/systematic/todo-resolve/ and deleting resolved todo files. It also interacts with Git to commit and push changes to remote repositories.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by processing untrusted data from todo files.
  • Ingestion points: Reads Markdown files from .context/systematic/todos/*.md and todos/*.md (SKILL.md).
  • Boundary markers: None identified; the skill does not explicitly use delimiters or instructions to ignore instructions embedded within the todo files.
  • Capability inventory: Spawns sub-agents (systematic:workflow:pr-comment-resolver), writes to the file system, deletes files, and executes Git commands (commit/push).
  • Sanitization: No evidence of content validation or escaping of the ingested Markdown data before it is processed by the agent or sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 03:11 PM
Security Audit — agent-trust-hub — todo-resolve