The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a bash script find-polluter.sh that executes npm test on files discovered via the find command. It also references a workspace helper tool executed through python <aegis-workspace-helper> in SKILL.md for project initialization and evidence management.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its primary function of processing external data.
Ingestion points: The agent is instructed to read and analyze potentially untrusted data including error messages, stack traces, and reproduction evidence as described in SKILL.md and root-cause-tracing.md.
Boundary markers: The instructions lack specific boundary markers or "ignore" directives to prevent the agent from mistakenly executing instructions that might be embedded within logs or test artifacts.
Capability inventory: The skill allows the agent to execute shell commands via npm and python utilities.
Sanitization: There is no evidence of sanitization, filtering, or validation of the diagnostic data before it is processed by the agent.

systematic-debugging