CC renatus-icm
Manage Renatus event marketing campaigns as an ICM. Use when running event registration campaigns, sending commercial email blasts, setting up event landing pages, exporting leads from Supabase, syncing unsubscribes to Renatus, or performing browser-based guest registration via CDP. Requires: Renatus credentials, Supabase project, SMTP sender account. Trigger phrases: "run a Renatus event campaign", "send Renatus email campaign", "register a guest for Renatus", "download Renatus leads", "set up event landing page".
As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
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.
How to improve
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
net-credential-usereferences/email-campaign.md:157Credential used in a network call (verify the destination is the intended service)curl -H "x-admin-token: $TOKEN" \
-
medium Exfiltration
net-credential-usereferences/workflows.md:148Credential used in a network call (verify the destination is the intended service)curl -H "x-admin-token: $TOKEN" \
-
medium Exfiltration
net-credential-usereferences/workflows.md:157Credential used in a network call (verify the destination is the intended service)curl -H "x-admin-token: $TOKEN" \
-
medium Exfiltration
net-credential-usereferences/workflows.md:164Credential used in a network call (verify the destination is the intended service)curl -s -H "x-admin-token: $TOKEN" \
-
medium Exfiltration
net-redirectable-api-keyscripts/renatus_leads.py:54Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
intent-browser-credential-storeSKILL.md:28Accesses a browser credential / cookie store (quoted — discussed, not commanded)**CDP access:** Scripts connect to `http://127.0.0.1:9222` to inspect your browser's localStorage/cookies for Renatus auth tokens. This requires Chrome/Brave launched with `--remote-debugging-port=922
quoted -
medium Exfiltration
net-credential-useSKILL.md:135Credential used in a network call (verify the destination is the intended service)curl -H "x-admin-token: $TOKEN" \
-
low Exfiltration
net-credential-usereferences/supabase-setup.md:85Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable; quoted — discussed, not commanded)4. Export: `curl -H "x-admin-token: $TOKEN" "https://<REF>.functions.supabase.co/lead-admin-export?limit=10"`
variable hostquoted -
low Dangerous commands
cmd-cron-mentionreferences/workflows.md:111Mentions editing / listing crontabcrontab -e
-
low Secrets in code
secret-high-entropy-tokenreferences/workflows.md:256High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- `Requ…ion`
quoted
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Manage Renatus event marketing campaigns as an ICM. Use when runni… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 18 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2782 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 520: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 10 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.