PostHog

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This looks like a legitimate PostHog helper, but it grants broad PostHog API authority and exposes account-changing actions without clear registry declarations or confirmation safeguards.

Install only if you want the agent to operate on your PostHog project. Use least-privilege API keys, set POSTHOG_HOST only to a trusted PostHog/self-hosted domain, and require explicit review before any create, update, delete, capture, or broad HogQL query.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

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.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

If given a broadly scoped key, the agent could read private analytics/person data and modify PostHog resources allowed by that key.

Why it was flagged

The skill asks for a personal PostHog API key and describes broad private API authority. This is purpose-aligned, but high-impact and under-declared relative to the supplied registry metadata, which lists no primary credential or required env vars.

Skill content
POSTHOG_API_KEY (required): Personal API key ... Private (personal API key): query, CRUD for all resources
Recommendation

Use a least-privilege PostHog key scoped only to the actions you need, and avoid giving a full personal/admin token unless necessary.

#
ASI02: Tool Misuse and Exploitation
Medium
What this means

A mistaken or over-eager agent action could change or delete a PostHog feature flag and affect users of the connected product.

Why it was flagged

The helper can create, update, and delete feature flags using the bearer token. Feature flags can affect production behavior, and the artifacts do not show confirmation prompts, dry-run mode, rollback guidance, or other safeguards for destructive/account-changing commands.

Skill content
create-flag) ... _post -d @- ... update-flag) ... _patch -d @- ... delete-flag) ... _del "$HOST/api/projects/$PROJECT/feature_flags/$1/"
Recommendation

Require explicit user confirmation before write/delete commands, prefer read-only keys for analysis tasks, and add clear rollback or review steps for feature flag changes.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Users may not see the required tools and credential needs from the registry metadata alone.

Why it was flagged

The registry metadata lacks provenance and does not declare the helper's practical dependencies or credentials, even though the included artifacts document API keys and a Bash/curl/jq helper. No hidden download or remote installer is shown.

Skill content
Source: unknown; Homepage: none; Required binaries: none; Env var declarations: none; Primary credential: none
Recommendation

Publish a source/homepage and declare the required environment variables, credential type, and helper dependencies in the registry metadata.