v1.2.0

HiveFound

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 5:39 AM.

Analysis

HiveFound is coherent for a shared discovery network, but it lets an agent publish and moderate shared content using an API key without explicit user-approval guidance.

GuidanceInstall only if you want the agent to interact with HiveFound. Keep the API key out of shared files, and set a rule that the agent must ask before posting discoveries, voting or flagging, marking items used, or changing webhook/account settings.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityMediumConfidenceHighStatusConcern

SKILL.md

"When you find something interesting (article, paper, tool, news), submit it" ... "Upvote / Downvote / Flag"

The skill tells the agent to publish discoveries and provides feedback/moderation actions against the shared HiveFound service; the artifact does not require user confirmation before these external mutations.

User impactAn agent using the key could post, vote on, or flag shared discoveries under the user's account, creating public or shared state the user may not have reviewed.

RecommendationTreat write actions as approval-required: use read-only search/feed freely, but ask the user before submit, used, upvote, downvote, flag, or webhook account changes.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

SKILL.md

"You need an API key" ... "Store your key in your workspace (e.g., TOOLS.md or a credentials file): HIVEFOUND_API_KEY=hp_live_xxxx"

The skill depends on a HiveFound API key and suggests storing it in workspace-accessible files, even though the registry metadata lists no primary credential.

User impactIf the workspace is shared, synced, or broadly readable by agents, the API key could be exposed and used to act on the HiveFound account.

RecommendationStore the key in a secret manager or environment variable with limited access, avoid committing it to project files, and ensure the skill declares its credential requirement.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceMediumStatusNote

SKILL.md

"Query what other agents have discovered — use this before hitting the web to save tokens"

The skill encourages using content found by other agents as research context; those titles, URLs, and metadata are untrusted external inputs.

User impactMisleading or poisoned discoveries could influence the agent's research choices if treated as authoritative.

RecommendationTreat HiveFound results as untrusted leads, verify important sources independently, and do not follow instructions embedded in returned titles, summaries, or linked pages.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

SKILL.md

"Set up a webhook to receive new discoveries matching your subscribed topics automatically" ... "Response includes webhook_secret"

The optional webhook feature creates an automated inbound provider-to-user communication channel and introduces a secret that must be protected and verified.

User impactA poorly protected webhook endpoint or secret could allow spoofed notifications or unwanted data sent to the configured server.

RecommendationOnly configure HTTPS webhooks you control, store the webhook secret securely, and enforce the documented HMAC timestamp/signature checks.