The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external, potentially untrusted data. \n- Ingestion points: The skill takes 'Error message/logs' and 'Failing test ID' as inputs to drive its investigation (SKILL.md). \n- Boundary markers: There are no instructions or delimiters provided to the agent to treat input logs as untrusted data or to ignore instructions embedded within them. \n- Capability inventory: The skill has the ability to execute dynamic commands via 'helpmetest_run_interactive_command' and modify test files using 'helpmetest_upsert_test' (SKILL.md). \n- Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested log content before it is used to influence agent actions.

helpmetest-debugger