get_evidence
Retrieve evidence artifacts for an engagement or specific finding. Always returns the on-disk SHA-256 per artifact so callers can compare it against the hash stored in a finding's evidence_artifacts field to detect tampering. Args: include_content: read each artifact's file contents into content....
This record as markdown: /tools/0xsteph-pentest-ai/get-evidence.md
What get_evidence does on Pentest Ai
AI agents call get_evidence to retrieve information from Pentest Ai without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_evidence is rated Low
This tool retrieves and returns artifacts and their metadata (SHA-256 hashes, file contents, HTTP exchange details) without modifying, executing, or deleting anything. It is purely a data retrieval operation. The inclusion of content and parsing of existing captured data does not constitute execution of new operations or commands.
From the tool's definition Tool description states 'Retrieve evidence artifacts' and 'read each artifact's file contents into `content`'.
Attacks that exploit this kind of access
The rule that runs get_evidence safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Pentest Ai, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_evidence, this is the rule to start with:
get_evidence is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Pentest Ai, apply this rule, and every get_evidence call is checked against it from then on.
Questions about get_evidence
Retrieve evidence artifacts for an engagement or specific finding. Always returns the on-disk SHA-256 per artifact so callers can compare it against the hash stored in a finding's evidence_artifacts field to detect tampering. Args: include_content: read each artifact's file contents into content. as_curl: for http_request artifacts, parse the captured exchange and emit a copy-pasteable curl one-liner in curl. It is categorised as a Read tool in the Pentest Ai MCP Server, which means it retrieves data without modifying state.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for get_evidence: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pentest Ai. Nothing to install.
get_evidence is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_evidence rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_evidence. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_evidence is provided by the Pentest Ai MCP server (0xsteph/pentest-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Pentest Ai, and thousands of servers like it.
This server
Across the catalogue