crawler-access-audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze server logs and robots.txt content, which are external and attacker-controllable inputs. Maliciously crafted data in these files could attempt to influence the agent's behavior during the audit process.
- Ingestion points: Server log files and robots.txt files (referenced in SKILL.md sections 1 and 5).
- Boundary markers: The instructions mention handling malformed lines and quoted fields in SKILL.md section 5, but do not provide explicit delimiters or warnings for the agent to ignore instructions embedded within the log data.
- Capability inventory: The skill involves reading files, parsing timestamps, and performing CIDR containment checks to identify crawlers (SKILL.md sections 4 and 5).
- Sanitization: There is no mention of sanitizing or escaping the log content before it is processed by the agent.
Audit Metadata