The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from a codebase being audited, creating a potential surface for indirect prompt injection.\n
Ingestion points: The skill instructs the agent to read and search files within directories such as src/, k8s/, deploy/, and charts/ using command-line tools like grep and find (detailed in rules/06-audit-playbook.md).\n
Boundary markers: There are no explicit instructions for the agent to use boundary markers or to ignore instructions that may be embedded within the audited files.\n
Capability inventory: The skill utilizes the agent's capability to execute shell commands and read file system content to evaluate the observability posture of a system.\n
Sanitization: The skill does not provide mechanisms for sanitizing or escaping the untrusted data read from the codebase before it is processed by the agent.

sota-observability