techsmith-common-errors
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data such as error logs, failure symptoms, and redacted evidence, which could be exploited to influence agent behavior if malicious instructions are embedded within the logs.
- Ingestion points: External error text, command output, and log files provided by the user during the triage process (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or isolation techniques for processing untrusted strings, although they focus on redaction.
- Capability inventory: The skill has access to file system modification tools (
Write,Edit) and network capabilities (WebFetch) (SKILL.md). - Sanitization: The skill includes robust requirements for the user to redact all keys, account identifiers, and activation artifacts before the agent processes the evidence.
Audit Metadata