BF symbiont
Zero-trust AI agent governance for OpenClaw. Adds ORGA runtime, Cedar policy enforcement, SchemaPin tool verification, ClawHavoc skill scanning, and cryptographic audit trails. Use when you need agent governance, security policies, Cedar authorization, MCP tool verification, audit logging, or when scaffolding governed agent projects, scanning skills for malicious patterns, or writing Symbiont DSL definitions.
As a process F 52/100 · Will not run — References files that are not bundled: references/cedar-patterns.md, references/dsl-guide.md, scripts/audit-log.sh
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 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 text references files that are not there: add them or drop the references.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-destructive-fspolicy-guard.sh:30Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; documentation of a security skill)":(){ :|:& };:"code literalsecurity skill -
medium Dangerous commands
cmd-destructive-fspolicy-guard.sh:33Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; documentation of a security skill)"> /dev/sda"
code literalsecurity skill -
low Dangerous commands
cmd-privilegepolicy-guard.sh:31Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)"chmod -R 777 /"
code literalsecurity skill -
low Risky intent
intent-offensive-securitySKILL.md:205Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)The scanner covers: reverse shells, credential harvesting, network exfiltration, process injection, privilege escalation, symlink/path traversal, and downloader chains.
detector
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/cedar-patterns.md - warning
missing-refreference to a missing file: references/dsl-guide.md - warning
missing-refreference to a missing file: scripts/audit-log.sh - warning
missing-refreference to a missing file: scripts/policy-guard.sh
Process rating: all ten parameters 52/100
- 0Tools and files. 4 referenced file(s) missing: references/cedar-patterns.md, references/dsl-guide.md, scripts/audit-log.sh
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 7 branches
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2590 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 412: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.