agent-tools
5 findings (1 high, 1 medium, 2 low, 1 info), mainly data exfiltration, policy violation, command injection. Most recent scan 2026-10-22.
Byte-identical copies of this skill are also published by magentosh, qu-skills. Same SKILL.md, same files; each copy is scanned separately so divergence shows up here.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
- Package
- 5 files, 16 KB
- SKILL.md
- 687 words, 12+ sections
- Code
- None. Instructions only.
- Allowed tools
Bash(belt*)
SKILL.md covers: [inference.sh](https://inference.sh) · Install CLI · Quick Examples · Generate an image · Generate a video · Call Claude · Web search · Post to Twitter · Generate 3D model · Local File Uploads · Upscale a local image · Image-to-video from local file
Findings
HIGH Dangerous data flow in command pipeline Data Exfiltrationpipeline
Pipeline downloads data from the network and executes it: `curl -fsSL https://cli.inference.sh | sh`. This is a remote code execution pattern.
SKILL.md:1
curl -fsSL https://cli.inference.sh | shMEDIUM Network-derived content reaches code execution Command Injectioncorrelation
Correlated network → code_execution behavior across SKILL.md.
SKILL.md:18
LOW Dangerous data flow in command pipeline Data Exfiltrationpipeline
Pipeline downloads data from the network and executes it: `curl -fsSL https://cli.inference.sh | sh`. This is a remote code execution pattern. (Note: found in documentation file - may be instructional rather than executable.)
references/authentication.md:1
curl -fsSL https://cli.inference.sh | shLOW Dangerous data flow in command pipeline Data Exfiltrationpipeline
Pipeline downloads data from the network and executes it: `curl -fsSL https://cli.inference.sh | sh`. This is a remote code execution pattern. (Note: found in documentation file - may be instructional rather than executable.)
references/cli-reference.md:1
curl -fsSL https://cli.inference.sh | shINFO Skill does not specify a license Policy Violationstatic
Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.
SKILL.md
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 6.0 KB |
references/app-discovery.md | doc | 2.0 KB |
references/authentication.md | doc | 1.1 KB |
references/cli-reference.md | doc | 3.3 KB |
references/running-apps.md | doc | 3.6 KB |
External hosts referenced
inference.sh cli.inference.sh cloud.inference.sh dist.inference.sh docs.sigstore.dev
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
INFSH_API_KEY
Package contents recorded 2026-10-22 at commit becc25649700. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/101-skills/superpowers
- Raw scan result: 101-skills-superpowers-tools-agent-tools-scan.json
- Badge for your README:
- Request a re-scan