The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the faf-cli tool to perform auditing and scoring tasks. Commands include faf wjttc, faf wjttc --strict --json, and faf score --json.
[PERSISTENCE]: The skill provides instructions to create a persistent GitHub Actions workflow file. The command faf taf setup --write is used to generate .github/workflows/taf.yml, enabling automated code execution within the project's CI/CD environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as bug reproduction steps and test plans, which could be used to inject malicious instructions.
Ingestion points: Test plans, edge case definitions, and bug reproduction steps as described in the execution loop of SKILL.md.
Boundary markers: Absent; no specific delimiters or instructions to ignore embedded commands in the processed data are provided.
Capability inventory: Includes shell command execution through faf-cli and the ability to modify sensitive repository configuration files like CI workflows.
Sanitization: Absent; the skill does not specify any validation, escaping, or filtering of input data before processing.

wjttc-tester