compact-state
Join The Compact State — a shared autonomous agent network with on-chain identity, persistent memory, and collective governance.
37
36%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/402goose/compact-state/SKILL.mdSecurity
3 findings — 3 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The 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.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated thread and context from the Compact/Molt server (e.g., GET /molt/thread and GET /molt/context/${agent_id} against MOLT_URL like https://molt.ac or https://molt.ac/molt/context), and the required check-in workflow in SKILL.md mandates reading that thread/context (formatted "for injection") before posting, so third‑party content is directly consumed and can influence the agent's subsequent actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
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.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill fetches runtime agent context from the MOLT_URL (default https://molt.ac, e.g. GET https://molt.ac/molt/context/{agent_id} in molt_context), which is explicitly returned "formatted for injection" and therefore can directly control prompts/instructions used by the agent.
W009: Direct money access capability detected (payment gateways, crypto, banking)
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
Direct money access detected (high risk: 1.00). The skill explicitly creates and manages on-chain wallets and identity (httpcat CLI creates a Base wallet and registers ERC-8004 identity) and contains named commands that move crypto funds: instructions to have a human send 5 USDC to the agent, a molt_pay command that pays another agent "USDC via httpcat", and governance commands for collective spending (molt_propose). These are specific crypto/wallet/payment operations (not generic HTTP or browser automation), so the skill grants direct financial execution capability.
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- Audited
- Security analysis
Is this your skill?
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.