CC solo-mission
Use this skill for ANY interaction with the SOLO Mission Platform — creating missions, hiring humans, managing conversations, handling on-chain escrow (Solana; EscrowVault on Base is closed to new mission creation during the Solana private beta migration ahead of Solana mainnet), recovering stuck funds, or operating as an autonomous agent on solomission.ai. Trigger on phrases like "create a mission", "browse humans", "hire a participant", "settle a mission", "claim refund", "emergency refund", "SOLO platform", or any mention of the SOLO Mission API. Also trigger when the user asks you to act as a SOLO agent, register an agent, or send USDC rewards to participants. Also trigger on Solana-specific phrasing: "Solana mission", "fund on Solana", "SPL", "devnet", "Phantom", "solo_escrow", or any question about which chain a mission runs on.
Use this skill for ANY interaction with the SOLO Mission Platform — creating missions, hiring humans, managing conversations, handling on-chain escrow…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 9
✓ No critical or high findings
Medium and low: 9
-
medium Exfiltration
net-credential-usereferences/rest-api.md:335Credential used in a network call (verify the destination is the intended service)curl -s "$BASE/agent/missions?limit=100" -H "X-Agent-Key: $KEY" \
-
medium Exfiltration
net-credential-usereferences/rest-api.md:345Credential used in a network call (verify the destination is the intended service)HUMAN=$(curl -s "$BASE/agent/humans?limit=1" -H "X-Agent-Key: $KEY")
-
medium Exfiltration
net-credential-usereferences/rest-api.md:353Credential used in a network call (verify the destination is the intended service)curl -s "$BASE/agent/missions/$MISSION_ID" -H "X-Agent-Key: $KEY" | jq '.participants'
-
medium Exfiltration
net-credential-usereferences/rest-api.md:364Credential used in a network call (verify the destination is the intended service)curl -s -X POST "$BASE/agent/missions/$MISSION_ID/settle" -H "X-Agent-Key: $KEY"
-
medium Dangerous commands
cmd-pipe-to-shellreferences/wallet-setup.md:34Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- Foundry installed: `curl -L https://foundry.paradigm.xyz | bash && foundryup`
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:227Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)echo " curl -L https://foundry.paradigm.xyz | bash && foundryup"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/onchain.md:17High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**USDC:** `0x03…F7e` (6 decimals)
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/wallet-setup.md:136High-entropy token-like string (may be an id, hash or a credential)cast call 0x03…F7e \
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:258High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)USDC="0x03…F7e"
quoted
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 16502 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 510): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 16502 tokens: crowds the task out of the window
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 54 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 846: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +4Structure: 48 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (47 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.