The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute several local shell scripts and commands to perform maintenance, instrumentation, and environment setup.
Evidence: SKILL.md contains an instruction to execute ./scripts/log-skill.sh for usage logging.
Evidence: workflows/reproduce-issue.md contains instructions to execute ./scripts/push-env.sh for environment variable synchronization and npm run test for unit testing.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically logs and bug reports, which could contain malicious instructions meant to influence the agent's debugging behavior.
Ingestion points: templates/bug-report.template.md contains a placeholder for {Paste logs here}, and workflows/reproduce-issue.md involves processing user interaction data.
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the log data.
Capability inventory: The skill has the ability to execute shell scripts and access the environment via the command execution points identified above.
Sanitization: No sanitization or validation of the ingested log content is specified.

debug