BC greenhelix-agent-observability-stack
Agent Observability Stack: Distributed Tracing, Metrics, and Alerting for Multi-Agent Systems. Build a complete observability stack for agent commerce: OpenTelemetry integration, distributed tracing across agent calls, custom metrics, anomaly detection, dashboard design, SLA monitoring, and cost attribution. Includes detailed Python code examples with full API integration.
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
exfil-webhook-urlSKILL.md:2011Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)webhook_url="https://hooks.slack.com/services/T00/B00/xxx",
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 24198 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "type" - note
frontmatter-keyunknown frontmatter key "price_usd" - note
frontmatter-keyunknown frontmatter key "content_type" - note
frontmatter-keyunknown frontmatter key "executable" - note
frontmatter-keyunknown frontmatter key "install" - note
frontmatter-keyunknown frontmatter key "credentials"
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 24198 tokens: crowds the task out of the window
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 20 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 33 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 375: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (17 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.