cve
Known CVE exploitation — fingerprint CMS/framework/plugin version, look up CVE candidates via cve_lookup, retrieve PoCs via cve_poc_lookup, adapt the public exploit to the target, and confirm RCE. Use whenever the challenge tag is `cve`, recon fingerprinted a versioned service, or the challenge name hints at known vulnerable software (WordPress, Joomla, Apache Struts, Spring4Shell, Log4j, etc.).
72
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
3 findings: 1 critical severity, 1 high severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This file is an explicit offensive exploit playbook: it instructs fingerprinting targets, automated CVE lookup and PoC retrieval, adapting and executing exploits (including RCE), and post-exploit secret harvesting/exfiltration, which constitutes clearly malicious intent and abuse.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs the agent to run a "Credential/Secret Extraction After RCE Confirmed" sweep (e.g., harvesting .env, SSH keys, tokens), which requires reading and therefore outputting secret values verbatim, creating a high exfiltration risk.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly instructs downloading and executing untrusted PoC code locally (e.g. wget + python3 /tmp/cve_poc.py) and running adapted exploits and post-exploit harvesting, which directs the agent to execute potentially malicious actions on the machine it runs on.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
This skill’s required workflow fetches outsider-authored free text from public sources at runtime (e.g., downloads PoC content from github.com/raw.githubusercontent.com via `curl/wget` in Step 3), which is then read/parsed into the agent context (e.g., `grep/head` over `/tmp/cve_poc.md` / `/tmp/cve_poc.py`).
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly instructs fetching and adapting remote PoCs (including executing a downloaded Python PoC) from URLs such as https://raw.githubusercontent.com/<user>/<repo>/main/poc.py and https://raw.githubusercontent.com/trickest/cve/main/2018/CVE-2018-11776.md during runtime, which means external content is fetched and executed to control the agent's exploit actions.
- Repository
- PurpleAILAB/Decepticon
- Commit
e34afba
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.