Fictional Companion Forge

v1.0.0

Turn a fictional character from games, films, TV, novels, comics, or anime into a deployable OpenClaw companion agent. Use when the user names a character su...

0· 105·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the actual behavior: an instruction-only authoring workflow that reads bundled reference files or uses a generic analysis framework to produce the four core files. There are no unrelated required env vars, binaries, or config paths.
Instruction Scope
SKILL.md stays within the expected scope (generate soul.md, identity.md, memory.md, agents.md). It reads bundled reference files when present and defines clear content rules. One ambiguity: 'Gather canon facts, defining scenes, voice patterns, and fan interpretation signals' does not specify source or mechanism (agent knowledge vs. external web lookup). This is a functional ambiguity, not evidence of malicious intent.
Install Mechanism
Instruction-only skill with no install spec, no downloads, and no code files — minimal installation risk.
Credentials
No required environment variables, credentials, or config paths declared or used. The skill does not request access to unrelated services or secrets.
Persistence & Privilege
always:false and no claims of modifying other skills or system-wide settings. Normal autonomous invocation is allowed (platform default) but the skill does not request elevated permanent presence.
Assessment
This skill appears internally consistent and low-risk from a security/credential perspective, but consider a few non-security items before installing: - Source provenance: the skill bundles character reference files (Call of Duty characters). Confirm you are comfortable using potentially copyrighted characters and whether you need permissions for commercial use. - Canon sourcing: the SKILL.md is ambiguous about where 'canon facts' should come from — decide whether the agent should rely only on its internal knowledge and the bundled references or be allowed to fetch external web sources (granting web access raises additional risks). - Content safety: the skill explicitly preserves darker/violent edges and discourages 'softening' canonical trauma; if you plan to expose vulnerable users or minors to these companions, add mitigations (safety filters, explicit break-character crisis behavior is included but verify it meets your policy). - Hallucination risk: ask the skill to mark clearly where it is inferring beyond canon and provide provenance when users request factual claims. If you need higher assurance, request evidence of the author/source and a clearer statement of external-fetch behavior (e.g., 'agent will not access the web unless explicitly allowed by the user').

Like a lobster shell, security has layers — review code before you run it.

latestvk974csaxv5c6s1ectv52a554ah83gdv6

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments