The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external requirement specifications or 'specs' to produce detailed implementation plans.
Ingestion points: The overview and plan templates reference external 'spec/design docs' which are processed into the agent's context in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions to treat the input spec content as data rather than instructions, potentially allowing a malicious spec to influence plan generation.
Capability inventory: The skill generates implementation plans that include shell commands (git, pytest) and arbitrary code blocks for file creation and modification.
Sanitization: No explicit sanitization or validation of the requirements text is implemented.
[COMMAND_EXECUTION]: The implementation plans generated by this skill include specific shell commands like git add, git commit, and pytest. While these are standard tools in a development workflow, the skill relies on the integrity of the input requirement documents to ensure that the generated commands are appropriate and do not include malicious flags or unintended operations.

writing-plans