The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as error messages, stack traces, logs, and request bodies in Phase 1, creating a surface for indirect prompt injection attacks where malicious data could influence agent behavior.
Ingestion points: Untrusted diagnostic data enters the agent context via bug reports, error messages, stack traces, and session logs as described in SKILL.md.
Boundary markers: The skill does not provide delimiters or instructions to treat gathered data as untrusted, which could lead the agent to misinterpret data as instructions.
Capability inventory: The skill directs the agent to execute shell commands, write tests, and perform code modifications.
Sanitization: There are no documented steps for sanitizing or validating the input data before it is analyzed by the agent.
[COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command git log --oneline -30 to review recent commit history during the investigation process.

investigate-root-cause