The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a Python driver script via the Bash tool to manage the document generation lifecycle.
Evidence: python3 "${CLAUDE_PLUGIN_ROOT}/tools/saga_driver.py" --layer 08_IPLAN --allow-skip-permissions in SKILL.md.
[COMMAND_EXECUTION]: The instructions explicitly direct the agent to include a flag that bypasses user confirmation prompts for file operations. This is a deliberate reduction of security oversight to enable unattended operation.
Evidence: "--allow-skip-permissions lets the phases the driver dispatches write files without a permission prompt — unattended autopilot requires it." in SKILL.md.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from multiple sources to generate project artifacts with significant system access.
Ingestion points: SKILL.md identifies input from user prompts, SPEC/TDD components, and existing IPLAN files.
Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the ingested data.
Capability inventory: The skill uses the Bash tool to execute scripts and write files to the project directory.
Sanitization: Absent; no validation or sanitization steps are documented before processing external content.

doc-iplan-autopilot