Back to skill

Security audit

Deepwiki

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped DeepWiki helper for public GitHub repository research, with explicit checks to avoid sending private repository data to public services.

Install this only if you are comfortable with the agent sending public GitHub repository names and focused repository questions to GitHub and DeepWiki MCP. Do not use the public path for private repositories; follow the skill's Devin/private MCP guidance instead.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
This JSON test file contains natural-language prompts and expected behaviors exclusively in Traditional Chinese, effectively enforcing a specific language/locale for the skill interaction. The policy allows language constraints only when the user is given a choice or when the locale restriction is clearly justified, neither of which is present here.

External Transmission

Medium
Category
Data Exfiltration
Content
visibility_file="$(mktemp)"
trap 'rm -f "$visibility_file"' EXIT
visibility_http_code="$(curl -sS --location --max-time 15 --output "$visibility_file" --write-out '%{http_code}' \
  "https://api.github.com/repos/$repo_name")" || {
  printf '%s\n' '{"repositoryVisibility":"unknown","reason":"github-visibility-request-failed"}' >&2
  exit 1
}
Confidence
15% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Unbounded Resource Access

Medium
Category
Excessive Agency
Content
| Repository not found, private, or its visibility is uncertain | Verify the exact public GitHub `owner/repo` spelling and visibility before any public MCP call. | For private repositories, require an approved Devin account and Devin MCP integration; never send the repository name, URL, source, or metadata to public DeepWiki. |
| Tool names or schema no longer match the expected three capabilities | Re-run the bounded discovery once and inspect the returned tool names. | Report schema drift and use the direct public MCP procedure only when its standard tools are available and the repository is confirmed public. |
| Wiki structure is empty, sparse, or does not cover the needed subsystem | Ask one narrower `ask_question` naming the subsystem. | State that the generated wiki is incomplete and verify against repository source before making consequential claims. |
| Full wiki contents are too large or truncated | Stop the full-content request and retain the structure result. | Use `read_wiki_structure` plus focused `ask_question` calls; do not retry the same unbounded request. |
Confidence
24% confidence
Finding
Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Static analysis

No suspicious patterns detected.