identity-provider-attack
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external identity artifacts such as JWT tokens and SAML assertions, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill processes external identity data blocks as demonstrated in
payloads.mdandtest-cases.md(e.g., JWT strings, XML assertions). - Boundary markers: Absent. The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the processed identity data.
- Capability inventory: The skill utilizes
Bash,Write,Edit, andWebFetchtools, providing a broad capability set that could be abused if malicious instructions in an ingested token were executed. - Sanitization: Absent. There is no evidence of validation or sanitization routines for the tokens before they are processed by the agent's logic or passed to shell tools.
- [COMMAND_EXECUTION]: The skill provides instructions for executing various third-party security tools and scripts via the command line. While these are appropriate for offensive security testing, they involve executing external code.
- Evidence: References to
python3 jwt_tool.py,o365creeper.py,SAMLExtractor.py, and tools likemitm6,AADInternals, andROADtoolsinSKILL.md.
Audit Metadata