ad-overview
Active Directory attack lane — BloodHound ingestion, Kerberoasting, ADCS ESC scanning, DCSync, LAPS extraction.
63
75%
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
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/ad/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high 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
The content is an explicit offensive Active Directory playbook: step‑by‑step instructions for credential theft, DCSync/krbtgt exfiltration, NTLM coercion/relay, certificate-based impersonation, and post‑auth remote execution—clearly intended for deliberate 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 instructs constructing shell commands that embed plaintext credentials (e.g., -p pass) on the command line, which requires the LLM to output secret values verbatim and therefore poses an exfiltration risk.
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
The required runtime workflow in `bloodhound-bhce/SKILL.md` ingests outsider-authored free text via `bhce_ingest_zip` (SharpHound ZIP uploads originate from the operator/attacker and are parsed by the BHCE sidecar before `bhce_cypher` queries), so poison content can be introduced through that ingest step.
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 docs include runtime install-and-run commands that fetch and execute remote code (git clone https://github.com/p0dalirius/Coercer then sudo python3 Coercer.py, and git clone https://github.com/Pennyw0rth/NetExec && pipx install .), so these URLs are used at runtime to retrieve code that is then executed.
- Repository
- PurpleAILAB/Decepticon
- Commit
0cf691e
- 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.