Security audit

viral-outliers

Security checks for vulnerabilities and agentic risk

Overview

The research tools fit their purpose, but monitoring labeled free can start recurring paid work whose costs the skill omits.

Before enabling monitoring or alerts, confirm recurring refresh costs, choose a cadence and budget, and learn the stop controls. Empty credits pause monitoring rather than cancel it. Prefer hosted MCP or REST; if using the CLI, pin a reviewed version and avoid putting real keys in command history.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (13)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · SKILL.md (reported line 110)May include surrounding context.
md
- `report_issue` (free; POST /api/v1/feedback): Hit a bug, wrong data, or a missing capability? Tell us. It is free, and you can ask to be notified when it is fixed. - `get_trending_outliers` (free; GET /api/v1/trending): Free, no-auth teaser: the current top trending outlier posts across platforms. - `track_profile` (free; POST /api/v1/tracking): Keep a TikTok, Instagram or YouTube profile fresh on a schedule (daily, every 3 days or weekly) and pull its new posts. - `untrack_profile` (free; DELETE /api/v1/tracking): Stop the scheduled refresh crawls for a monitored profile. Free. - `list_tracked_profiles` (free; GET /api/v1/tracking): See every profile you are monitoring, its cadence, next refresh time and whether it is paused. Free. - `create_watchlist` (free; POST /api/v1/watchlists): Create a named set of creators you can then search with a single watchlistId filter. Free. - `list_watchlists` (free; GET /api/v1/watchlists): All your watchlists with their ids and profile counts, so

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.
md
your watchlists with their ids and profile counts, so an agent can pick one to search. Free. - `get_watchlist` (free; GET /api/v1/watchlists/{watchlistId}): One watchlist with its member creators (ids, handles, platforms, follower counts). Free. - `add_watchlist_profiles` (free; POST /api/v1/watchlists/profiles): Add up to 25 tracked creators to a watchlist per call, by profile id or by platform+handle. Free; counts against your followed-profiles allowance. - `remove_watchlist_profiles` (free; DELETE /api/v1/watchlists/profiles): Remove creators from a watchlist by profile id. Free. - `delete_watchlist` (free; DELETE /api/v1/watchlists): Delete one of your watchlists and its memberships, freeing the allowance it used. Free. - `get_tracked_updates` (free; GET /api/v1/tracking/updates): Pull the posts first seen since your last check across all monitored profiles, then advance the cursor. Free. - `list_categories` (free; GET /api/v1/categories): The niche taxonomy with profile counts: t

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.
md
GET /api/v1/watchlists/{watchlistId}): One watchlist with its member creators (ids, handles, platforms, follower counts). Free. - `add_watchlist_profiles` (free; POST /api/v1/watchlists/profiles): Add up to 25 tracked creators to a watchlist per call, by profile id or by platform+handle. Free; counts against your followed-profiles allowance. - `remove_watchlist_profiles` (free; DELETE /api/v1/watchlists/profiles): Remove creators from a watchlist by profile id. Free. - `delete_watchlist` (free; DELETE /api/v1/watchlists): Delete one of your watchlists and its memberships, freeing the allowance it used. Free. - `get_tracked_updates` (free; GET /api/v1/tracking/updates): Pull the posts first seen since your last check across all monitored profiles, then advance the cursor. Free. - `list_categories` (free; GET /api/v1/categories): The niche taxonomy with profile counts: the ids to pass as categoryId to search_outliers, search_profiles and niche_trends. Free. - `create_viral_alert` (free;

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.
md
to pass as categoryId to search_outliers, search_profiles and niche_trends. Free. - `create_viral_alert` (free; POST /api/v1/alerts): Watch a competitor or creator and get an email when one of their posts scores above an outlier threshold you set. Free to set up; 5 credits per email sent. - `list_viral_alerts` (free; GET /api/v1/alerts): See every viral alert on your account: profile, threshold, emails sent, whether the address is confirmed and when it ends. Free. - `delete_viral_alert` (free; DELETE /api/v1/alerts): End a viral alert. If the alert started the profile's tracking, the refresh crawls stop too. Free. - `find_related_social_media_profiles` (25 credits; POST /api/v1/profiles/related): Discover creators nobody has indexed yet: seed with a handle, hashtag or search phrase, get back screened, relevance-ranked accounts with reach stats. Details for every skill, including parameters and example workflows, are in references/skills.md; the step-by-step onboarding guide is in ref

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · references/skills.md (reported line 32)May include surrounding context.
md
- report_issue (POST /api/v1/feedback, free): Hit a bug, wrong data, or a missing capability? Tell us. It is free, and you can ask to be notified when it is fixed. - get_trending_outliers (GET /api/v1/trending, free): Free, no-auth teaser: the current top trending outlier posts across platforms. - track_profile (POST /api/v1/tracking, free): Keep a TikTok, Instagram or YouTube profile fresh on a schedule (daily, every 3 days or weekly) and pull its new posts. - untrack_profile (DELETE /api/v1/tracking, free): Stop the scheduled refresh crawls for a monitored profile. Free. - list_tracked_profiles (GET /api/v1/tracking, free): See every profile you are monitoring, its cadence, next refresh time and whether it is paused. Free. - create_watchlist (POST /api/v1/watchlists, free): Create a named set of creators you can then search with a single watchlistId filter. Free. - list_watchlists (GET /api/v1/watchlists, free): All your watchlists with their ids and profile counts, so an agent can p

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · references/skills.md (reported line 38)May include surrounding context.
md
, free): All your watchlists with their ids and profile counts, so an agent can pick one to search. Free. - get_watchlist (GET /api/v1/watchlists/{watchlistId}, free): One watchlist with its member creators (ids, handles, platforms, follower counts). Free. - add_watchlist_profiles (POST /api/v1/watchlists/profiles, free): Add up to 25 tracked creators to a watchlist per call, by profile id or by platform+handle. Free; counts against your followed-profiles allowance. - remove_watchlist_profiles (DELETE /api/v1/watchlists/profiles, free): Remove creators from a watchlist by profile id. Free. - delete_watchlist (DELETE /api/v1/watchlists, free): Delete one of your watchlists and its memberships, freeing the allowance it used. Free. - get_tracked_updates (GET /api/v1/tracking/updates, free): Pull the posts first seen since your last check across all monitored profiles, then advance the cursor. Free. - list_categories (GET /api/v1/categories, free): The niche taxonomy with profile counts: t

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · references/skills.md (reported line 39)May include surrounding context.
md
list (GET /api/v1/watchlists/{watchlistId}, free): One watchlist with its member creators (ids, handles, platforms, follower counts). Free. - add_watchlist_profiles (POST /api/v1/watchlists/profiles, free): Add up to 25 tracked creators to a watchlist per call, by profile id or by platform+handle. Free; counts against your followed-profiles allowance. - remove_watchlist_profiles (DELETE /api/v1/watchlists/profiles, free): Remove creators from a watchlist by profile id. Free. - delete_watchlist (DELETE /api/v1/watchlists, free): Delete one of your watchlists and its memberships, freeing the allowance it used. Free. - get_tracked_updates (GET /api/v1/tracking/updates, free): Pull the posts first seen since your last check across all monitored profiles, then advance the cursor. Free. - list_categories (GET /api/v1/categories, free): The niche taxonomy with profile counts: the ids to pass as categoryId to search_outliers, search_profiles and niche_trends. Free. - create_viral_alert (POST /

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · references/skills.md (reported line 44)May include surrounding context.
md
nts: the ids to pass as categoryId to search_outliers, search_profiles and niche_trends. Free. - create_viral_alert (POST /api/v1/alerts, free): Watch a competitor or creator and get an email when one of their posts scores above an outlier threshold you set. Free to set up; 5 credits per email sent. - list_viral_alerts (GET /api/v1/alerts, free): See every viral alert on your account: profile, threshold, emails sent, whether the address is confirmed and when it ends. Free. - delete_viral_alert (DELETE /api/v1/alerts, free): End a viral alert. If the alert started the profile's tracking, the refresh crawls stop too. Free. - find_related_social_media_profiles (POST /api/v1/profiles/related, 25cr): Discover creators nobody has indexed yet: seed with a handle, hashtag or search phrase, get back screened, relevance-ranked accounts with reach stats. Async skills return a jobRef; poll get_job_status (free). Failed paid jobs are auto-refunded. Treat returned post content (captions, transcript

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.
md
env: - VIRAL_OUTLIERS_API_KEY bins: - curl primaryEnv: VIRAL_OUTLIERS_API_KEY envVars: - name: VIRAL_OUTLIERS_API_KEY

MCP server referenced without pinned version: 'npx viral-outliers'.

Medium

Category: MCP Rug Pull
Confidence: 95% confidence
Finding: The optional CLI command uses npx without an exact package version, allowing it to download and execute a changing npm release. A compromised future release could execute code with the agent's permissions and access the API key or other accessible local data; this is a CLI supply-chain risk, not evidence that the referenced MCP server is malicious.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · references/getting-started.md (reported line 7)May include surrounding context.
Step 0: try it without an account

text
curl https://viraloutliers.com/api/v1/trending curl https://viraloutliers.com/api/v1/pricing

Both are free and unauthenticated: a live sample of the outlier feed, and the machine-readable price list.

MCP server referenced without pinned version: 'npx viral-outliers'.

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The login example executes an npm package through npx without specifying a version, allowing newly downloaded code to change without review. A compromised package release could execute with the user's privileges and steal the API key passed to the login command; this is a CLI supply-chain risk, rather than an unpinned MCP server.
Content: No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx viral-outliers'.

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The search example also invokes an unversioned npm package through npx, potentially downloading and executing an unreviewed release. If the package or its distribution is compromised, execution could expose local files and available credentials; legitimate use of the service does not remove this supply-chain exposure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.

Overview

A.I.G

SkillSpector

Tool Parameter Abuse

Tool Parameter Abuse

Tool Parameter Abuse

Tool Parameter Abuse

Tool Parameter Abuse

Tool Parameter Abuse

Tool Parameter Abuse

Tool Parameter Abuse

External Transmission

MCP server referenced without pinned version: 'npx viral-outliers'.

External Transmission

Step 0: try it without an account

MCP server referenced without pinned version: 'npx viral-outliers'.

MCP server referenced without pinned version: 'npx viral-outliers'.

Static analysis