skills/mukul975/anthropic-cybersecurity-skills/analyzing-cobaltstrike-malleable-c2-profiles/Gen Agent Trust Hub
analyzing-cobaltstrike-malleable-c2-profiles
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of
dissect.cobaltstrikeandpyMalleableC2. These are standard, well-known third-party Python libraries used for cybersecurity research and C2 profile analysis, hosted on public registries.\n- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its design of ingesting untrusted configuration data to generate automated outputs.\n - Ingestion points: The
scripts/agent.pyscript reads user-supplied C2 profile files or JSON data through the--inputcommand-line argument.\n - Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard malicious directives embedded within the profile content during processing.\n
- Capability inventory: The skill has the capability to write files to the local file system (via
args.output), allowing the persistent storage of potentially malicious or injected rule sets.\n - Sanitization: The
generate_suricata_rulesfunction inagent.pyperforms basic escaping of double quotes but lacks comprehensive validation of the content extracted from URI and pipe fields, which could allow a crafted profile to inject malicious rule logic into the generated Suricata signatures.
Audit Metadata