Build or troubleshoot portal JSON/native login clients, refresh, Documents, profile and admin APIs, and public JWKS. Use for HTTP contracts; portal Caddyfile wiring belongs to configuration-authentication.
77%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.codex/skills/authentication-portal-api/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The skill's runtime paths are portal HTTP APIs, native login, and Documents operations that read the user's own tenant data or authenticated colleague-shared content, but the connected-accounts HTML page can render display identity strings from an external provider account that an outsider controls, and the agent reads it only after actively fetching that page.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The decisive boundary is that the skill imports and builds the Go module `github.com/greenpau/go-authcrunch`, an explicit remote repository locator, so it is an operational code dependency; greenpau is an individual-owned repository, making it unofficial rather than strong first-party provenance, so the tier is medium, while the Chromium links are static citations and do not count.
greenpau/caddy-security
3225a2b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.