The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external test logs and JUnit XML artifacts which are untrusted data sources. An attacker capable of influencing test output could embed malicious instructions aimed at influencing the agent's subsequent actions. * Ingestion points: CI log files and XML result files located in .github/, test-results/, Saved/Logs/, or target/nextest/ as specified in sections 2 and 3 of SKILL.md. * Boundary markers: The instructions do not define clear delimiters or provide 'ignore embedded instructions' warnings when parsing external log data. * Capability inventory: The skill utilizes Bash, Write, and Edit tools, allowing for shell command execution and file modification. * Sanitization: There is no explicit mention of sanitizing, escaping, or validating the external content before it is processed or interpolated into reports.

test-flakiness