ClawHub
Back to skill

Security audit

startup-launch-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only public startup research helper that uses a third-party API, with no hidden persistence, destructive behavior, or privilege escalation found.

Install only if you are comfortable sending startup research queries and target identifiers to Crawlora using your Crawlora API key. Treat TrustMRR, Product Hunt, and Kickstarter results as public point-in-time signals, avoid secrets or private diligence material in requests, and keep any broad directory collection within applicable terms and consent expectations.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill includes shell usage examples (`scripts/crawlora.sh ...`) but does not declare any explicit tool scope such as `permissions` or `allowed-tools`. That creates an authorization ambiguity where an agent or runtime may permit broader shell access than intended, increasing the risk of command execution beyond the narrowly expected API-wrapper calls. The skill’s research context is relatively low sensitivity, but undeclared shell capability still weakens containment and makes prompt or parameter injection more dangerous if this skill is reused in a less constrained environment.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The file states that requests are sent to an external API using an API key but gives no user-facing disclosure that input parameters and requested targets will be transmitted off-platform. This can lead to uninformed handling of sensitive queries, identifiers, or research targets and weakens informed consent around credentialed network activity.

External Transmission

Medium
Category
Data Exfiltration
Content
Endpoints this skill uses, grouped by platform. Call them via `scripts/crawlora.sh` (see SKILL.md).

All paths are relative to the API base `https://api.crawlora.net/api/v1` and require the header `x-api-key: $CRAWLORA_API_KEY`. Path params like `{id}` are substituted into the URL; `GET` params go in the query string; `POST` params go in a JSON body.

**22 endpoints across 3 platform group(s).**
Confidence
80% confidence
Finding
This file documents direct external transmission to `api.crawlora.net` with a privileged API key, which is inherently security-relevant in an agent skill because user-supplied query terms and targets leave the local environment. The skill context makes this somewhat expected for web research, but still dangerous without clear safeguards because it can expose sensitive research interests or enable broad third-party data retrieval.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The documented `trustmrr_startups` endpoint explicitly enables enumeration of the full TrustMRR directory and pairs with the detail endpoint to scrape all startup profiles at scale. That exceeds a narrow launch-research use case and creates a capability for bulk collection of commercially sensitive business metadata, increasing abuse risk even if the data is nominally public.

External Transmission

Medium
Category
Data Exfiltration
Content
#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
# Usage:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
# Usage:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
# config supplies the header and is removed automatically on exit.
umask 077
curl_config="$(mktemp "${TMPDIR:-/tmp}/crawlora-curl.XXXXXX")"
chmod 600 "$curl_config"
trap 'rm -f "$curl_config"' EXIT
printf 'header = "x-api-key: %s"\n' "$CRAWLORA_API_KEY" >"$curl_config"
auth=(--config "$curl_config")
Confidence
80% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Vague Triggers

Low
Confidence
81% confidence
Finding
The endpoint reference provides operational details but no local trigger scope, authorization boundaries, or invocation constraints in the file itself. In a tool-using agent, vague scope increases the chance the skill is invoked for broader collection or unintended external calls beyond the user's expectation.

Static analysis

No suspicious patterns detected.