The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and interprets instructions from local documentation files to drive its autonomous workflow, which could allow malicious instructions in those files to influence agent behavior.
Ingestion points: The skill reads docs/STORIES.md, design/DESIGN-SYSTEM.md, and docs/GLOSSARY.md (found in SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when processing these files.
Capability inventory: The skill has the ability to execute shell scripts (./build.sh), write to the filesystem (code and documentation), and perform source control operations (git) (found in SKILL.md).
Sanitization: There is no evidence of sanitization or validation of the content read from the external files before it is processed by the agent.
[COMMAND_EXECUTION]: The skill automates the execution of local shell commands and git operations to perform build and commit tasks.
Evidence: Execution of ./build.sh, ./build.sh --open, git add -A, and git commit are defined in the autonomous loop instructions (found in SKILL.md).

improve-loop