Back to skill

Security audit

oldnavy-research

Security checks for vulnerabilities and agentic risk

Overview

The skill is a constrained shopping-research helper that sends requested catalog and location queries to Crawlora, with no evidence of hidden data collection or persistence.

Before installing, be comfortable sending your Crawlora API key plus search terms, product IDs, and optional ZIP code or coordinates to Crawlora. Avoid placing unrelated sensitive information into helper arguments, especially because the script currently accepts POST bodies even though the documented workflow only needs GET requests.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/crawlora.sh:34
Finding
Undocumented POST support permits arbitrary data transmission to the external API<![CDATA[ ## Vulnerability Details **File Location**: `scripts/crawlora.sh`, lines 34-38, 45-52, and 85-103 **Vulnerability Type**: Excessive network capability and insufficient request-method restriction **Risk Level**: Medium ### Vulnerable Code ```sh while [ $# -gt 0 ]; do case "$1" in -X) method="$2"; shift 2 ;; -d) body="$2"; shift 2 ;; *) args+=("$1"); shift ;; esac done ``` ```sh case "$method" in GET|POST) ;; *) echo "only GET and POST are supported by the oldnavy-research skill" >&2 exit 2 ;; esac ``` ```sh if [ "$method" = "GET" ]; then # -G + --data-urlencode URL-encodes each value (so spaces etc. are safe). qs=() for kv in ${rest[@]+"${rest[@]}"}; do [ -n "$kv" ] || continue # curl treats both @file and name@file forms as local-file input for # --data-urlencode. Reject @ outright so query arguments cannot disclose # local files to the Crawlora API. case "$kv" in *@*) echo "@ is not allowed in query arguments" >&2; exit 2 ;; esac qs+=(--data-urlencode "$kv") done curl -fsS -G "${auth[@]}" ${qs[@]+"${qs[@]}"} "${base}${path}" else [ -n "$body" ] || body="${rest[0]:-}" [ -n "$body" ] || body='{}' # Stream the body on stdin so curl never interprets a user value as its # @file shorthand (and cannot read local files supplied in a request body). printf '%s' "$body" | curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" --data-binary @- "${base}${path}" fi ``` ### Technical Analysis All seven endpoints documented in `reference/endpoints.md` use HTTP GET. Nevertheless, the helper accepts `-X POST` and `-d`, then forwards an arbitrary caller-controlled body to the fixed Crawlora API origin. This capability is not required for the skill's declared product-search, category, review, store-location, or availability operations. It therefore exceeds the minimum network privileges necessary for the documented functionality. The script does not vali ...[truncated 2763 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Remove POST and request-body support because every documented endpoint is GET-only: ```sh case "$method" in GET) ;; *) echo "only GET is supported by the oldnavy-research skill" >&2 exit 2 ;; esac ``` 2. Remove parsing for `-d`, the `body` variable, and the POST branch so arbitrary payloads cannot be forwarded. 3. Prefer eliminating `-X` entirely and always invoke curl with GET semantics. 4. Validate query parameter names separately for each allowlisted endpoint. Reject unknown fields and enforce expected types and ranges for `brand`, `cid`, `pid`, `page`, `zip`, `lat`, `lng`, `store_id`, and `search`. 5. Avoid placing sensitive user content into product-search or location parameters unless it is strictly required and the user has knowingly requested the external lookup. 6. If POST endpoints are added later, maintain an explicit method-to-path allowlist and a strict body schema for each endpoint rather than enabling POST globally. 7. Document that search terms, ZIP codes, and coordinates are transmitted to Crawlora before requesting location-related data. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill clearly instructs use of a shell helper (`scripts/crawlora.sh`) but does not declare any explicit tool scope such as `permissions` or `allowed-tools`. That creates a governance gap: an agent may be permitted broader shell access than necessary, increasing the chance of unintended command execution or misuse beyond the narrow API-calling purpose of the skill.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
This markdown file documents use of an API key header and later endpoints that accept precise location inputs, but it does not include any warning that requests may transmit sensitive credential or location data. Under the markdown-specific SQP-2 criteria, descriptions should warn about behaviors that could affect user privacy or system integrity.

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.
#
Confidence
70% 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.

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.

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
# Keep the API key out of the curl process command line. A private temporary
# config supplies the header and is removed automatically on exit.
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.

External Transmission

Medium
Category
Data Exfiltration
Content
[ -n "$body" ] || body='{}'
  # Stream the body on stdin so curl never interprets a user value as its
  # @file shorthand (and cannot read local files supplied in a request body).
  printf '%s' "$body" | curl -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" --data-binary @- "${base}${path}"
fi
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.