The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard development commands such as npm test, pytest, npm run lint, and grep. These are used for project-specific tasks like running test suites, verifying type safety, and scanning for secrets or debug artifacts.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection attack surface by ingesting and processing untrusted data (external codebases).
Ingestion points: In assets/modes/INIT.md, the agent performs a 'Deep Analysis' of the codebase using Glob, Grep, and Read tools.
Boundary markers: The generated findings and sprint templates do not implement specific delimiters or instructions to ignore malicious content embedded within the analyzed code.
Capability inventory: The agent is granted Bash, Edit, Write, and Task capabilities, which are used to modify the codebase and execute commands based on the generated plan.
Sanitization: There is no evidence of automated sanitization or escaping of code content before it is summarized into findings or tasks.

sprint-forge