The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes an 'Audit mode' where sub-agents analyze existing codebases to evaluate observability coverage. This ingestion of untrusted code content represents a surface for indirect prompt injection.
Ingestion points: Source code files and project structures read during the audit process via the Read, Glob, and Grep tools.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from executing commands embedded in the audited files.
Capability inventory: The agent has access to powerful tools including Edit, Write, and Bash, which could be targeted by an injection attack.
Sanitization: No explicit sanitization or validation of the audited code is defined in the skill instructions.
[SAFE]: The skill provides strong security guidance, such as advising developers to avoid logging personally identifiable information (PII) and ensuring that sensitive debugging endpoints like pprof are not publicly accessible.
[SAFE]: All external links point to official documentation (e.g., Prometheus, Grafana, Go) or established open-source repositories that are appropriate for the skill's technical domain.

golang-observability