The Agent Skills Directory

[SAFE]: The skill's logic is consistent with its stated purpose of gathering requirements and generating project briefs. No evidence of hardcoded credentials, data exfiltration, or malicious persistence was found.
[COMMAND_EXECUTION]: The skill requests the Bash tool in the allowed-tools section of its configuration. While the current instructions do not specify any dangerous shell commands, the availability of a full shell environment provides a high-privilege capability that could be abused if the agent is compromised.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it utilizes WebSearch and WebFetch to ingest content from the internet for competitive analysis. This untrusted data could contain hidden instructions designed to manipulate the agent's behavior.
Ingestion points: Web data retrieved via WebSearch and WebFetch as described in the Research Enhancement section of SKILL.md.
Boundary markers: Absent. The instructions do not define delimiters or provide specific 'ignore' directives for the data retrieved from external URLs.
Capability inventory: The skill is configured with powerful tools including Bash, Write, and Edit, which could be used to perform unauthorized file modifications or system actions if an injection is successful.
Sanitization: Absent. There is no mention of sanitizing, filtering, or validating external content before it is incorporated into the agent's context.

forge-brief