Is inference-sh/skills/ai-social-media-content safe?

suspiciouslow confidence
34/100

context safety score

A score of 34/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.

identity
45
behavior
39
content
24
graph
57

7 threat patterns detected

low

supply chain

Found 64 install-script pattern(s) in documentation (likely install instructions, not executable)

low

supply chain

Found 64 remote script pattern(s) in documentation (likely install instructions, not executable)

medium

shadow chaining

SKILL.md references 6 external package/skill installation(s)

critical

supply chain

Skill instructs curl-pipe-to-shell installation (curl -fsSL https://cli.inference.sh | sh) of an external CLI binary from a completely unverifiable source. The publisher has 0 stars, 0 forks, 0 contributors, unknown account age, no license, not listed on any registry, and no org verification. The claimed 7.69M installs is wildly inconsistent with 0 stars/forks, suggesting fabricated metrics. There is no way to verify the SHA-256 claim or the safety of the binary. (location: SKILL.md:16)

high

description injection

The SKILL.md frontmatter description is aggressively keyword-stuffed with 30+ trigger phrases (tiktok, instagram reels, youtube shorts, viral content, ugc content, ai influencer, etc.) designed to maximize agent selection probability across many queries. Combined with the metadata anomaly where skill_description contains an HTML meta viewport tag ('width=device-width, initial-scale=1') instead of a real description, this indicates systematic gaming of skill discovery mechanisms. (location: SKILL.md:3, metadata.json:skill_description)

medium

shadow chaining

The 'Related Skills' section instructs installing 5 additional skills from the same unverified publisher (inference-sh/skills@ai-video-generation, ai-image-generation, twitter-automation, text-to-speech, inference-sh). Given the publisher has zero trust signals, this creates an attack chain that progressively expands the agent's attack surface through an untrusted supply chain. (location: SKILL.md:233-248)

medium

scope violation

allowed-tools grants Bash(infsh *) which permits execution of any command prefixed with 'infsh'. While ostensibly scoped to the infsh CLI, the skill also contains bash workflow examples with shell constructs (for loops, variable expansion, piping to files) that go beyond simple CLI invocation. Combined with the unverified binary installed via curl|sh, the effective scope is arbitrary code execution through an untrusted binary. (location: SKILL.md:4)

API

curl https://api.brin.sh/skill/inference-sh%2Fskills%2Fai-social-media-content

FAQ: how to interpret this assessment

Common questions teams ask before deciding whether to use this skill in agent workflows.

Is inference-sh/skills/ai-social-media-content safe for AI agents to use?

inference-sh/skills/ai-social-media-content currently scores 34/100 with a suspicious verdict and low confidence. The goal is to protect agents from high-risk context before they act on it. Treat this as a decision signal: higher scores suggest lower observed risk, while lower scores mean you should add review or block this skill.

How should I interpret the score and verdict?

Use the score as a policy threshold: 80–100 is safe, 50–79 is caution, 20–49 is suspicious, and 0–19 is dangerous. Teams often auto-allow safe, require human review for caution/suspicious, and block dangerous.

How does brin compute this skill score?

brin evaluates four dimensions: identity (source trust), behavior (runtime patterns), content (malicious instructions), and graph (relationship risk). Analysis runs in tiers: static signals, deterministic pattern checks, then AI semantic analysis when needed.

What do identity, behavior, content, and graph mean for this skill?

Identity checks source trust, behavior checks unusual runtime patterns, content checks for malicious instructions, and graph checks risky relationships to other entities. Looking at sub-scores helps you understand why an entity passed or failed.

Why does brin scan packages, repos, skills, MCP servers, pages, and commits?

brin performs risk assessments on external context before it reaches an AI agent. It scores that context for threats like prompt injection, hijacking, credential harvesting, and supply chain attacks, so teams can decide whether to block, review, or proceed safely.

Can I rely on a safe verdict as a full security guarantee?

No. A safe verdict means no significant risk signals were detected in this scan. It is not a formal guarantee; assessments are automated and point-in-time, so combine scores with your own controls and periodic re-checks.

When should I re-check before using an entity?

Re-check before high-impact actions such as installs, upgrades, connecting MCP servers, executing remote code, or granting secrets. Use the API in CI or runtime gates so decisions are based on the latest scan.

Learn more in threat detection docs, how scoring works, and the API overview.

Last Scanned

February 28, 2026

Verdict Scale

safe80–100
caution50–79
suspicious20–49
dangerous0–19

Disclaimer

Assessments are automated and may contain errors. Findings are risk indicators, not confirmed threats. This is a point-in-time assessment; security posture can change.

start scoring agent dependencies.

integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.