Individual skill
audit-agent-surface
Inventory what agents can reach in a pracht app (capability exposure, `agents` trust config, MCP auth, `llms.txt`, Markdown, OpenAPI) and report anything wider than intended. Use for "audit the agent surface", "what can agents do on my site", "is my MCP endpoint safe", "did this PR widen agent access".
skills/audit-agent-surface/SKILL.md
Source commit e7c088a615e0bc16659d7a307fe92910ae6bd546
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 106
- Repository last updated
- Nov 9, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- cloudflare-workers Repository topic
- framework Repository topic
- full-stack Repository topic
- llms-txt Repository topic
- mcp Repository topic
- preact Repository topic
- ssg Repository topic
- ssr Repository topic
- security Derived category
- docs Derived category
- docs-api Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
Read excerpt
# Pracht Audit Agent Surface
pracht's agent surface is opt-in end to end (<https://pracht.resynapse.dev/docs/agents>). State that baseline before
auditing the opt-outs:
- No loader or API route is ever inferred as a capability; a capability without
`expose` is unreachable over the network.
- `destructive` capabilities may be exposed over HTTP and remote MCP, never as
WebMCP page tools, and every dispatch is confirmation-gated.
- Remote MCP rejects cookie-bearing requests and browser origins not listed in
`agents.mcp.allowedOrigins`, and serves destructive capabilities only with
`agents.mcp.destructive` plus a registered approval store — otherwise it
filters them out. `agents.mcp.auth` makes it an OAuth 2.0 protected resource;
without it the endpoint is open and authentication is middleware's job.