The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from spec.md and clarify decision files, which are potentially untrusted inputs.
Ingestion points: Reads from spec.md and clarify data during the plan generation phase.
Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for processing these files.
Capability inventory: The skill executes adlc-cli for workflow management and runs local shell scripts (run-branch.sh, open-mr.sh) for branch and merge request operations.
Sanitization: There is no evidence of sanitization or validation of the content read from input files before it influences agent actions.
[COMMAND_EXECUTION]: The skill's primary function involves executing shell commands and scripts to manage automation workflows.
Evidence: Instructions include running adlc-cli workflow state show, adlc-cli workflow resume, and executing local scripts like run-branch.sh and open-mr.sh.
[EXTERNAL_DOWNLOADS]: The skill references a dependency hosted in an external repository.
Evidence: Recommends installation from tikalk/adlc-team-skills via adlc-cli skills add.

mission-plan