The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests content from local project files that could contain instructions designed to influence the agent's behavior during plan generation.
Ingestion points: ROADMAP.md, gap-reports/, scorecards/, launch-gaps.md, and tech.md (found in SKILL.md).
Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore embedded commands within the analyzed data.
Capability inventory: The skill has the ability to execute Bash (git, cp), Write to output directories, and Edit a configuration file (jaan-to/config/settings.yaml).
Sanitization: Absent. ROADMAP task descriptions are used to map to skill invocations without explicit validation or escaping.
[DYNAMIC_EXECUTION]: The skill dynamically loads local shell scripts to provide utility functions for ID generation and index updates.
Evidence: Use of the source command in Phase 2 to load ${CLAUDE_PLUGIN_ROOT}/scripts/lib/id-generator.sh and ${CLAUDE_PLUGIN_ROOT}/scripts/lib/index-updater.sh.
[COMMAND_EXECUTION]: The skill utilizes restricted bash commands to interact with the project's version control and file system.
Evidence: Bash(git log:*), Bash(git diff:*), and Bash(cp:*) are declared in the allowed-tools metadata.

pm-sprint-plan