DC gha-security-review
Review GitHub Actions workflows for exploitable vulnerabilities with concrete attack paths and harmless proof-of-concept sketches. Require explicit authorization for active testing.
Review GitHub Actions workflows for exploitable vulnerabilities with concrete attack paths and harmless proof-of-concept sketches.
As a process C 61/100 · Has gaps — weak spots: result and completion, failures and branches, progress reporting
The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills
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 · 14
✓ No critical or high findings
Medium and low: 14
-
medium Exfiltration
exfil-read-secret-filesreferences/runner-infrastructure.md:41Reads credential / secret files (documentation of a security skill)cat ~/.docker/config.json # Docker registry credentials
security skill -
medium Exfiltration
exfil-read-secret-filesreferences/runner-infrastructure.md:42Reads credential / secret files (documentation of a security skill)cat ~/.npmrc # npm tokens
security skill -
medium Exfiltration
exfil-read-secret-filesreferences/runner-infrastructure.md:43Reads credential / secret files (documentation of a security skill)cat ~/.aws/credentials # AWS credentials from previous deployments
security skill -
low Risky intent
intent-offensive-securityreferences/real-world-attacks.md:272Offensive-security / dual-use content (legitimate for authorised testing; review intended use)1. **Same attacker infrastructure:** All attacks used `hackmoltrepeat.com` for payload delivery
-
low Risky intent
intent-offensive-securityreferences/real-world-attacks.md:273Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. **Same payload delivery:** `UNTRUSTED_REMOTE_EXECUTION` pattern in every attack
A further 9 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "date_added"
Process rating: all ten parameters 61/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 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
- 85Steps. 39 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2323 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +1No license
- +2Single-language instructions
- +3Description length 181: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.