Caveat verdict

ctf-ai-ml

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Reads local files AND makes external network calls

A CTF challenge reference skill for AI/ML attack techniques (adversarial examples, model extraction, prompt injection) used in legitimate security competitions; all commands are documented research techniques for solving CTF puzzles, not directed at real targets.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
60
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 · LLM06 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Prompt injection — tries to override agent instructions

SKILL.md · code · Ignore previous instructions

Pattern match critical

Uses eval() — can execute arbitrary code

adversarial-ml.md · code · eval(

Pattern match critical

Accesses sensitive system files

llm-attacks.md · code · /etc/passwd

Pattern match high

Possible prompt injection — attempts to redefine agent identity

llm-attacks.md · code · You are now

Pattern match high

os.system/popen — direct OS command execution

llm-attacks.md · code · os.popen(

Pattern match high

HTTP request to bare IP address — common in malicious payloads

llm-attacks.md · code · http://169.254.169.254

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installnetwork_outnetwork_infile_read
Check another skill Browse the registry Auditing your own skills or configs? Use the API