pave-catalog
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core function of processing external and potentially untrusted repository data.
- Ingestion points: The agent is instructed to discover services by scanning deployment configurations, CI files, Terraform, Kubernetes manifests, and docker-compose files (SKILL.md Step 2).
- Boundary markers: The instructions lack explicit delimiters or warnings to treat external content as data only, increasing the risk that the agent might follow embedded instructions within those files.
- Capability inventory: The skill is permitted to use Bash, Write, and Edit tools (SKILL.md frontmatter), which could be exploited if a malicious file containing instructions is processed.
- Sanitization: There are no specific instructions to sanitize or validate the content extracted from external configuration files before the agent processes them.
Audit Metadata