edge-recon
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to audit infrastructure settings and provide optimization recommendations. The tools used (Bash, WebFetch, Read) are appropriate for its stated purpose of inspecting CDN configurations and HTTP headers.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external sources.
- Ingestion points: Step 1 reads existing CDN configurations and response headers from external servers.
- Boundary markers: There are no specific instructions or delimiters used to separate the gathered configuration data from the agent's core instructions.
- Capability inventory: The agent has access to tools including
Bash,Read,Write, andWebFetchas defined in the frontmatter. - Sanitization: The instructions do not include steps to sanitize or filter the contents of the retrieved headers or configurations before processing.
Audit Metadata